refdb.bib

@Article{abadi2016-deep,
  author          = {{Abadi}, M. and {Chu}, A. and {Goodfellow}, I. and {Brendan McMahan}, H. and {Mironov}, I. and {Talwar}, K. and
                  {Zhang}, L.},
  title           = {{Deep Learning With Differential Privacy}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jul,
  eprint          = {1607.00133},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {security, privacy},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{abadi2016-learning,
  author          = {{Abadi}, M. and {Andersen}, D.~G.},
  title           = {{Learning To Protect Communications With Adversarial Neural Cryptography}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = oct,
  eprint          = {1610.06918},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Cryptography and Security, Computer Science - Learning},
  primaryclass    = "cs.CR",
  timestamp       = {20181201T1029}
}

@InProceedings{abadi2016-tensorflow,
  author          = {Martin Abadi and Paul Barham and Jianmin Chen and Zhifeng Chen and Andy Davis and Jeffrey Dean and Matthieu Devin and
                  Sanjay Ghemawat and Geoffrey Irving and Michael Isard and Manjunath Kudlur and Josh Levenberg and Rajat Monga and Sherry
                  Moore and Derek G. Murray and Benoit Steiner and Paul Tucker and Vijay Vasudevan and Pete Warden and Martin Wicke and Yuan
                  Yu and Xiaoqiang Zheng},
  title           = {TensorFlow: A system for large-scale machine learning},
  year            = 2016,
  booktitle       = {12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)},
  pages           = {265--283},
  url             = {https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf},
  timestamp       = {20181201T1029}
}

@Article{achille2017-emergence,
  author          = {{Achille}, A. and {Soatto}, S.},
  title           = {{On the Emergence of Invariance and Disentangling in Deep Representations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.01350},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {disentangle},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@InProceedings{achlioptas2002-sampling,
  author          = {Achlioptas, Dimitris and McSherry, Frank and Sch{\"o}lkopf, Bernhard},
  title           = {Sampling techniques for kernel methods},
  year            = 2002,
  booktitle       = {Advances in neural information processing systems},
  pages           = {335--342},
  keywords        = {random, kernel, quantization},
  timestamp       = {20181201T1029}
}

@InProceedings{achterhold2018-variational,
  author          = {Jan Achterhold and Jan Mathias Koehler and Anke Schmeink and Tim Genewein},
  title           = {Variational Network Quantization},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=ry-TW-WAb},
  timestamp       = {20181201T1029}
}

@InProceedings{adebayo2018-sanity,
  author          = {Adebayo, Julius and Gilmer, Justin and Muelly, Michael and Goodfellow, Ian and Hardt, Moritz and Kim, Been},
  title           = {Sanity checks for saliency maps},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {9524--9535},
  timestamp       = {20181224T0943}
}

@InProceedings{adhikari2012-multiresolution,
  author          = {Adhikari, Prem Raj and Hollm{\'e}n, Jaakko},
  title           = {Multiresolution Mixture Modeling using Merging of Mixture Components.},
  year            = 2012,
  booktitle       = {ACML},
  pages           = {17--32},
  timestamp       = {20181201T1029}
}

@Article{adi2016-fine,
  author          = {{Adi}, Y. and {Kermany}, E. and {Belinkov}, Y. and {Lavi}, O. and {Goldberg}, Y.},
  title           = {{Fine-Grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = aug,
  eprint          = {1608.04207},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1029}
}

@Article{advani2013-statistical,
  author          = {{Advani}, M. and {Lahiri}, S. and {Ganguli}, S.},
  title           = {{Statistical Mechanics of Complex Neural Systems and High Dimensional data}},
  journaltitle    = {Journal of Statistical Mechanics: Theory and Experiment},
  year            = 2013,
  volume          = 3,
  month           = mar,
  pages           = 03014,
  doi             = {10.1088/1742-5468/2013/03/P03014},
  eprint          = {1301.7115},
  url             = {https://doi.org/10.1088/1742-5468/2013/03/P03014},
  journal         = {Journal of Statistical Mechanics: Theory and Experiment},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2013JSMTE..03..014A},
  archiveprefix   = "arXiv",
  primaryclass    = "q-bio.NC",
  timestamp       = {20181201T1029}
}

@Article{advani2017-high,
  author          = {Advani, Madhu S and Saxe, Andrew M},
  title           = {High-Dimensional Dynamics of Generalization Error in Neural Networks},
  journaltitle    = {arXiv preprint arXiv:1710.03667},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1710.03667},
  timestamp       = {20181201T1029}
}

@Article{agarwal2016-second,
  author          = {{Agarwal}, N. and {Bullins}, B. and {Hazan}, E.},
  title           = {{Second Order Stochastic Optimization in Linear Time}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = feb,
  eprint          = {1602.03943},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@InProceedings{aggarwal2001-surprising,
  author          = {Aggarwal, Charu C. and Hinneburg, Alexander and Keim, Daniel A.},
  title           = {On the Surprising Behavior of Distance Metrics in High Dimensional Spaces},
  year            = 2001,
  booktitle       = {Proceedings of the 8th International Conference on Database Theory},
  series          = {ICDT '01},
  publisher       = {Springer-Verlag},
  isbn            = {3-540-41456-8},
  pages           = {420--434},
  url             = {http://dl.acm.org/citation.cfm?id=645504.656414},
  acmid           = 656414,
  address         = {London, UK, UK},
  keywords        = {high dimension, distance},
  numpages        = 15,
  timestamp       = {20181201T1029}
}

@Article{agliari2014-walk,
  author          = {{Agliari}, E. and {Barra}, A. and {Galluzzi}, A. and {Tantari}, D. and {Tavani}, F.},
  title           = {{A Walk in the Statistical Mechanical Formulation of Neural networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = jul,
  eprint          = {1407.5300},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2014arXiv1407.5300A},
  archiveprefix   = "arXiv",
  keywords        = {theory, spin glass, random graph},
  primaryclass    = "cond-mat.dis-nn",
  timestamp       = {20181201T1029}
}

@Article{agustsson2018-generative,
  author          = {{Agustsson}, E. and {Tschannen}, M. and {Mentzer}, F. and {Timofte}, R. and {Van Gool}, L.},
  title           = {{Generative Adversarial Networks for Extreme Learned Image Compression}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = apr,
  eprint          = {1804.02958},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180402958A},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1029}
}

@InProceedings{akat2008-particle,
  author          = {S. B. Akat and V. Gazi},
  title           = {Particle Swarm Optimization with Dynamic Neighborhood Topology: Three Neighborhood Strategies and Preliminary Results},
  year            = 2008,
  booktitle       = {2008 IEEE Swarm Intelligence Symposium},
  month           = {Sept},
  pages           = {1-8},
  doi             = {10.1109/SIS.2008.4668298},
  url             = {https://doi.org/10.1109/SIS.2008.4668298},
  keywords        = {pso},
  timestamp       = {20181201T1029}
}

@Article{akhtar2018-threat,
  author          = {{Akhtar}, N. and {Mian}, A.},
  title           = {{Threat of Adversarial Attacks on Deep Learning in Computer Vision: a Survey}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.00553},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180100553A},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, survey},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1029}
}

@Article{akiba2017-extremely,
  author          = {Takuya Akiba and Shuji Suzuki and Keisuke Fukuda},
  title           = {Extremely Large Minibatch {SGD:} Training Resnet-50 on Imagenet in 15 Minutes},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.04325},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@Article{alain2014-what,
  author          = {Alain, Guillaume and Bengio, Yoshua},
  title           = {What Regularized Auto-Encoders Learn From the Data-Generating Distribution},
  journaltitle    = {The Journal of Machine Learning Research},
  year            = 2014,
  volume          = 15,
  number          = 1,
  pages           = {3563--3593},
  journal         = {The Journal of Machine Learning Research},
  publisher       = {JMLR. org},
  timestamp       = {20181201T1029}
}

@Article{albert2002-statistical,
  author          = {Albert, R{\'e}ka and Barab{\'a}si, Albert-L{\'a}szl{\'o}},
  title           = {Statistical Mechanics of Complex Networks},
  journaltitle    = {Reviews of modern physics},
  year            = 2002,
  volume          = 74,
  number          = 1,
  pages           = 47,
  journal         = {Reviews of modern physics},
  publisher       = {APS},
  timestamp       = {20181201T1029}
}

@InCollection{alistarh2017-qsgd,
  author          = {Alistarh, Dan and Grubic, Demjan and Li, Jerry and Tomioka, Ryota and Vojnovic, Milan},
  title           = {QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1707--1718},
  url             = {http://papers.nips.cc/paper/6768-qsgd-communication-efficient-sgd-via-gradient-quantization-and-encoding.pdf},
  keywords        = {parallel, sgd},
  timestamp       = {20181201T1029}
}

@Article{almahairi2015-dynamic,
  author          = {Amjad Almahairi and Nicolas Ballas and Tim Cooijmans and Yin Zheng and Hugo Larochelle and Aaron C. Courville},
  title           = {Dynamic Capacity Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.07838},
  journal         = {CoRR},
  keywords        = {dynamic},
  timestamp       = {20181201T1029}
}

@Article{alvarez2002-neural,
  author          = {Alvarez, Alberto},
  title           = {A Neural Network With Evolutionary Neurons},
  journaltitle    = {Neural processing letters},
  year            = 2002,
  volume          = 16,
  number          = 1,
  pages           = {43--52},
  journal         = {Neural processing letters},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@Article{alvarez2016-decomposeme,
  author          = {Jose M. Alvarez and Lars Petersson},
  title           = {Decomposeme: Simplifying Convnets for End-To-End Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.05426},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1029}
}

@Article{alvarez2016-learning,
  author          = {Jose M. Alvarez and Mathieu Salzmann},
  title           = {Learning the Number of Neurons in Deep Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.06321},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@InCollection{alvarez2017-compression,
  author          = {Alvarez, Jose M and Salzmann, Mathieu},
  title           = {Compression-aware Training of Deep Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {856--867},
  url             = {http://papers.nips.cc/paper/6687-compression-aware-training-of-deep-networks.pdf},
  keywords        = {compression, regularizer, low rank},
  timestamp       = {20181201T1029}
}

@Article{amari1998-natural,
  author          = {Amari, Shun-Ichi},
  title           = {Natural Gradient Works Efficiently in Learning},
  journaltitle    = {Neural computation},
  year            = 1998,
  volume          = 10,
  number          = 2,
  pages           = {251--276},
  journal         = {Neural computation},
  publisher       = {MIT Press},
  timestamp       = {20181201T1029}
}

@InProceedings{amid2015-multiview,
  author          = {Amid, Ehsan and Ukkonen, Antti},
  title           = {Multiview triplet embedding: Learning attributes in multiple maps},
  year            = 2015,
  booktitle       = {Proceedings of the 32nd International Conference on Machine Learning (ICML-15)},
  pages           = {1472--1480},
  timestamp       = {20181201T1029}
}

@Article{ammar2016-one,
  author          = {Waleed Ammar and George Mulcaire and Miguel Ballesteros and Chris Dyer and Noah A. Smith},
  title           = {One Parser, Many Languages},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.01595},
  eprint          = {1602.01595},
  url             = {http://arxiv.org/abs/1602.01595},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/AmmarMBDS16},
  timestamp       = {20181201T1029}
}

@Article{amodei2016-concrete,
  author          = {Dario Amodei and Chris Olah and Jacob Steinhardt and Paul Christiano and John Schulman and Dan Man{\'{e}}},
  title           = {Concrete Problems in {AI} Safety},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.06565},
  url             = {http://arxiv.org/abs/1606.06565},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/AmodeiOSCSM16},
  timestamp       = {20181201T1029}
}

@InProceedings{amsaleg2017-vulnerability,
  author          = {Amsaleg, Laurent and Bailey, James and Barbe, Dominique and Erfani, Sarah and Houle, Michael E and Nguyen, Vinh and
                  Radovanovi{\'c}, Milo{\v{s}}},
  title           = {The Vulnerability of Learning to Adversarial Perturbation Increases with Intrinsic Dimensionality},
  year            = 2017,
  booktitle       = {Information Forensics and Security (WIFS), 2017 IEEE Workshop on},
  organization    = {IEEE},
  pages           = {1--6},
  keywords        = {adversarial, hypothesis},
  timestamp       = {20181201T1029}
}

@Article{andor2016-globally,
  author          = {Daniel Andor and Chris Alberti and David Weiss and Aliaksei Severyn and Alessandro Presta and Kuzman Ganchev and Slav
                  Petrov and Michael Collins},
  title           = {Globally Normalized Transition-Based Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.06042},
  url             = {http://arxiv.org/abs/1603.06042},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/AndorAWSPGPC16},
  timestamp       = {20181201T1029}
}

@Article{andrews1996-lexical,
  author          = {Andrews, Sally},
  title           = {Lexical Retrieval and Selection Processes: Effects of Transposed-Letter Confusability},
  keywords        = {brain, linguistic, psycho},
  journaltitle    = {Journal of Memory and Language},
  year            = 1996,
  volume          = 35,
  number          = 6,
  pages           = {775--800},
  journal         = {Journal of Memory and Language},
  publisher       = {Academic Press},
  timestamp       = {20190106T1052}
}

@InProceedings{anjos2011-counter,
  author          = {Anjos, Andr{\'e} and Marcel, S{\'e}bastien},
  title           = {Counter-measures to photo attacks in face recognition: a public database and a baseline},
  year            = 2011,
  booktitle       = {Biometrics (IJCB), 2011 international joint conference on},
  organization    = {IEEE},
  pages           = {1--7},
  timestamp       = {20181201T1029}
}

@Article{anonymous2018-thermometer,
  author          = {Anonymous},
  title           = {Thermometer Encoding: One Hot Way To Resist Adversarial Examples},
  journaltitle    = {International Conference on Learning Representations},
  year            = 2018,
  url             = {https://openreview.net/forum?id=S18Su--CW},
  journal         = {International Conference on Learning Representations},
  timestamp       = {20181201T1029}
}

@Article{anselmi2016-invariance,
  author          = {Anselmi, Fabio and Rosasco, Lorenzo and Poggio, Tomaso},
  title           = {On Invariance and Selectivity in Representation Learning},
  journaltitle    = {Information and Inference: A Journal of the IMA},
  year            = 2016,
  volume          = 5,
  number          = 2,
  pages           = {134--158},
  journal         = {Information and Inference: A Journal of the IMA},
  publisher       = {Oxford University Press},
  timestamp       = {20181201T1029}
}

@Article{antonik2018-using,
  author          = {Piotr Antonik and Marvyn Gulina and Ja{\"{e}}l Pauwels and Serge Massar},
  title           = {Using a Reservoir Computer To Learn Chaotic Attractors, With Applications To Chaos Synchronisation and Cryptography},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1802.02844},
  eprint          = {1802.02844},
  url             = {http://arxiv.org/abs/1802.02844},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1802-02844},
  keywords        = {chaos, reservior},
  timestamp       = {20181201T1029}
}

@InProceedings{anwar2015-fixed,
  author          = {Anwar, Sajid and Hwang, Kyuyeon and Sung, Wonyong},
  title           = {Fixed point optimization of deep convolutional neural networks for object recognition},
  year            = 2015,
  booktitle       = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  organization    = {IEEE},
  pages           = {1131--1135},
  keywords        = {quantization, lloyd-max},
  timestamp       = {20181201T1029}
}

@Article{anwar2015-structured,
  author          = {Sajid Anwar and Kyuyeon Hwang and Wonyong Sung},
  title           = {Structured Pruning of Deep Convolutional Neural Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.08571},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1029}
}

@Article{arandjelovic2017-look,
  author          = {Arandjelovi{\'c}, Relja and Zisserman, Andrew},
  title           = {Look, Listen and Learn},
  journaltitle    = {arXiv preprint arXiv:1705.08168},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.08168},
  timestamp       = {20181201T1029}
}

@InCollection{arjomand2017-deep,
  author          = {Arjomand Bigdeli, Siavash and Zwicker, Matthias and Favaro, Paolo and Jin, Meiguang},
  title           = {Deep Mean-Shift Priors for Image Restoration},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {763--772},
  url             = {http://papers.nips.cc/paper/6678-deep-mean-shift-priors-for-image-restoration.pdf},
  timestamp       = {20181201T1029}
}

@Article{arjovsky2015-unitary,
  author          = {Mart{\'{\i}}n Arjovsky and Amar Shah and Yoshua Bengio},
  title           = {Unitary Evolution Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06464},
  url             = {http://arxiv.org/abs/1511.06464},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ArjovskySB15},
  timestamp       = {20181201T1029}
}

@Article{arjovsky2017-towards,
  author          = {Arjovsky, Martin and Bottou, L{\'e}on},
  title           = {Towards Principled Methods for Training Generative Adversarial Networks},
  journaltitle    = {arXiv preprint arXiv:1701.04862},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1701.04862},
  timestamp       = {20181201T1029}
}

@Article{arjovsky2017-wasserstein,
  author          = {{Arjovsky}, M. and {Chintala}, S. and {Bottou}, L.},
  title           = {{Wasserstein GAN}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jan,
  eprint          = {1701.07875},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {wgan},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@InProceedings{arora2014-provable,
  author          = {Arora, Sanjeev and Bhaskara, Aditya and Ge, Rong and Ma, Tengyu},
  title           = {Provable Bounds for Learning Some Deep Representations.},
  year            = 2014,
  booktitle       = {ICML},
  pages           = {584--592},
  keywords        = {random},
  timestamp       = {20181201T1029}
}

@Article{arora2015-random,
  author          = {Sanjeev Arora and Yuanzhi Li and Yingyu Liang and Tengyu Ma and Andrej Risteski},
  title           = {Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1502.03520},
  eprint          = {1502.03520},
  url             = {http://arxiv.org/abs/1502.03520},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/AroraLLMR15},
  timestamp       = {20190109T1245}
}

@Article{arora2016-linear,
  author          = {Sanjeev Arora and Yuanzhi Li and Yingyu Liang and Tengyu Ma and Andrej Risteski},
  title           = {Linear Algebraic Structure of Word Senses, With Applications To Polysemy},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1601.03764},
  eprint          = {1601.03764},
  url             = {http://arxiv.org/abs/1601.03764},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/AroraLLMR16},
  timestamp       = {20181201T1029}
}

@Article{arora2017-generalization,
  author          = {Sanjeev Arora and Rong Ge and Yingyu Liang and Tengyu Ma and Yi Zhang},
  title           = {Generalization and Equilibrium in Generative Adversarial Nets (gans)},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.00573},
  url             = {http://arxiv.org/abs/1703.00573},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Arora0LMZ17},
  keywords        = {gan, mode collapse, theory, neural net distance},
  timestamp       = {20181201T1029}
}

@Article{arora2017-provable,
  author          = {Arora, Sanjeev and Risteski, Andrej},
  title           = {Provable Benefits of Representation Learning},
  journaltitle    = {arXiv preprint arXiv:1706.04601},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.04601},
  keywords        = {representation learning, theory},
  timestamp       = {20181201T1029}
}

@Article{arora2017-simple,
  author          = {Sanjeev Arora and Yingyu Liang and Tengyu Ma},
  title           = {A Simple But Tough-To-Beat Baseline for Sentence Embeddings},
  keywords        = {embedding, sentence},
  journaltitle    = {International Conference on Learning Representations},
  year            = 2017,
  journal         = {International Conference on Learning Representations},
  timestamp       = {20190103T1603}
}

@InProceedings{arora2018-do,
  author          = {Sanjeev Arora and Andrej Risteski and Yi Zhang},
  title           = {Do {GAN}s learn the distribution? Some Theory and Empirics},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BJehNfW0-},
  timestamp       = {20181201T1029}
}

@InProceedings{arp2014-drebin,
  author          = {Arp, Daniel and Spreitzenbarth, Michael and Hubner, Malte and Gascon, Hugo and Rieck, Konrad and Siemens, CERT},
  title           = {DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket.},
  year            = 2014,
  booktitle       = {Ndss},
  volume          = 14,
  pages           = {23--26},
  keywords        = {data, drebin},
  timestamp       = {20181201T1029}
}

@Article{arpit2016-normalization,
  author          = {{Arpit}, D. and {Zhou}, Y. and {Kota}, B.~U. and {Govindaraju}, V.},
  title           = {{Normalization Propagation: a Parametric Technique for Removing Internal Covariate Shift in Deep Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = mar,
  eprint          = {1603.01431},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{arpit2017-closer,
  author          = {{Arpit}, D. and {Jastrz{\c e}bski}, S. and {Ballas}, N. and {Krueger}, D. and {Bengio}, E. and {Kanwal}, M.~S. and
                  {Maharaj}, T. and {Fischer}, A. and {Courville}, A. and {Bengio}, Y. and {Lacoste-Julien}, S.},
  title           = {{A Closer Look At Memorization in Deep Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.05394},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {generalization, effective capacity},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{arpit2019-benefits,
  author          = {{Arpit}, Devansh and {Bengio}, Yoshua},
  title           = {{The Benefits of Over-Parameterization At Initialization in Deep Relu Networks}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1901.03611},
  month           = Jan,
  pages           = {arXiv:1901.03611},
  eprint          = {1901.03611},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/\#abs/2019arXiv190103611A},
  archiveprefix   = {arXiv},
  keywords        = {data, imagenet},
  primaryclass    = {stat.ML},
  timestamp       = {20190120T0824}
}

@InProceedings{artetxe2017-learning,
  author          = {Artetxe, Mikel and Labaka, Gorka and Agirre, Eneko},
  title           = {Learning bilingual word embeddings with (almost) no bilingual data},
  year            = 2017,
  booktitle       = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  volume          = 1,
  pages           = {451--462},
  timestamp       = {20181201T1029}
}

@Article{artetxe2017-unsupervised,
  author          = {{Artetxe}, M. and {Labaka}, G. and {Agirre}, E. and {Cho}, K.},
  title           = {{Unsupervised Neural Machine Translation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.11041},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171011041A},
  archiveprefix   = "arXiv",
  keywords        = {unsupervised, nmt, translation},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1029}
}

@InProceedings{ashok2018-n2n,
  author          = {Anubhav Ashok and Nicholas Rhinehart and Fares Beainy and Kris M. Kitani},
  title           = {N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=B1hcZZ-AW},
  timestamp       = {20181201T1029}
}

@Article{athalye2017-synthesizing,
  author          = {Anish Athalye and Logan Engstrom and Andrew Ilyas and Kevin Kwok},
  title           = {Synthesizing Robust Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.07397},
  journal         = {CoRR},
  keywords        = {adversarial, attack, eot},
  timestamp       = {20181201T1029}
}

@Article{athalye2018-obfuscated,
  author          = {{Athalye}, A. and {Carlini}, N. and {Wagner}, D.},
  title           = {{Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses To Adversarial Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.00420},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180200420A},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, hypothesis, obfuscated gradients},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{athiwaratkun2017-multimodal,
  author          = {{Athiwaratkun}, B. and {Wilson}, A.~G.},
  title           = {{Multimodal Word Distributions}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = apr,
  eprint          = {1704.08424},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv170408424A},
  archiveprefix   = "arXiv",
  keywords        = {gaussian mixtures, gm},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@InProceedings{auerbach2012-automated,
  author          = {Auerbach, Joshua E},
  title           = {Automated evolution of interesting images},
  year            = 2012,
  booktitle       = {Artificial Life 13},
  number          = {EPFL-CONF-191282},
  organization    = {MIT Press},
  timestamp       = {20181201T1029}
}

@InProceedings{ba2013-adaptive,
  author          = {Ba, Jimmy and Frey, Brendan},
  title           = {Adaptive dropout for training deep neural networks},
  year            = 2013,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {3084--3092},
  timestamp       = {20181201T1029}
}

@InCollection{ba2014-do,
  author          = {Ba, Jimmy and Caruana, Rich},
  title           = {Do Deep Nets Really Need to be Deep?},
  year            = 2014,
  booktitle       = {Advances in Neural Information Processing Systems 27},
  editor          = {Z. Ghahramani and M. Welling and C. Cortes and N. D. Lawrence and K. Q. Weinberger},
  publisher       = {Curran Associates, Inc.},
  pages           = {2654--2662},
  url             = {http://papers.nips.cc/paper/5484-do-deep-nets-really-need-to-be-deep.pdf},
  timestamp       = {20181201T1029}
}

@InCollection{ba2015-learning,
  author          = {Ba, Jimmy and Salakhutdinov, Ruslan R and Grosse, Roger B and Frey, Brendan J},
  title           = {Learning Wake-Sleep Recurrent Attention Models},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2593--2601},
  url             = {http://papers.nips.cc/paper/5861-learning-wake-sleep-recurrent-attention-models.pdf},
  timestamp       = {20181201T1029}
}

@Article{babaeizadeh2016-noiseout,
  author          = {Mohammad Babaeizadeh and Paris Smaragdis and Roy H. Campbell},
  title           = {Noiseout: {A} Simple Way To Prune Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.06211},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1029}
}

@InProceedings{babenko2009-similarity,
  author          = {Babenko, Boris and Branson, Steve and Belongie, Serge},
  title           = {Similarity metrics for categorization: from monolithic to category specific},
  year            = 2009,
  booktitle       = {2009 IEEE 12th International Conference on Computer Vision},
  organization    = {IEEE},
  pages           = {293--300},
  timestamp       = {20181201T1029}
}

@InProceedings{baccianella2010-sentiwordnet,
  author          = {Baccianella, Stefano and Esuli, Andrea and Sebastiani, Fabrizio},
  title           = {Sentiwordnet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining},
  year            = 2010,
  booktitle       = {Lrec},
  volume          = 10,
  number          = 2010,
  pages           = {2200--2204},
  keywords        = {data, sentiwordnet},
  timestamp       = {20181201T1029}
}

@Article{bach2015-pixel,
  author          = {Bach, Sebastian and Binder, Alexander and Montavon, Gr{\'e}goire and Klauschen, Frederick and M{\"u}ller, Klaus-Robert
                  and Samek, Wojciech},
  title           = {On Pixel-Wise Explanations for Non-Linear Classifier Decisions By Layer-Wise Relevance Propagation},
  journaltitle    = {PloS one},
  year            = 2015,
  volume          = 10,
  number          = 7,
  pages           = {e0130140},
  journal         = {PloS one},
  keywords        = {interpret},
  publisher       = {Public Library of Science},
  timestamp       = {20181201T1029}
}

@Article{bach2017-breaking,
  author          = {Bach, Francis},
  title           = {Breaking the Curse of Dimensionality With Convex Neural Networks},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2017,
  volume          = 18,
  number          = 19,
  pages           = {1--53},
  journal         = {Journal of Machine Learning Research},
  timestamp       = {20181201T1029}
}

@InCollection{bachman2015-data,
  author          = {Bachman, Philip and Precup, Doina},
  title           = {Data Generation as Sequential Decision Making},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3249--3257},
  url             = {http://papers.nips.cc/paper/5759-data-generation-as-sequential-decision-making.pdf},
  timestamp       = {20181201T1029}
}

@InProceedings{back1994-selective,
  author          = {T. Back},
  title           = {Selective pressure in evolutionary algorithms: a characterization of selection mechanisms},
  year            = 1994,
  booktitle       = {Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE
                  Conference on},
  month           = Jun,
  pages           = {57-62 vol.1},
  doi             = {10.1109/ICEC.1994.350042},
  url             = {https://doi.org/10.1109/ICEC.1994.350042},
  timestamp       = {20181201T1029}
}

@InProceedings{baeck1991-extended,
  author          = {Thomas B{\"a}ck and Frank Hoffmeister},
  title           = {Extended Selection Mechanisms in Genetic Algorithms},
  year            = 1991,
  booktitle       = {ICGA},
  timestamp       = {20181201T1029}
}

@Article{bahdanau2014-neural,
  author          = {Dzmitry Bahdanau and Kyunghyun Cho and Yoshua Bengio},
  title           = {Neural Machine Translation By Jointly Learning To Align and Translate},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1409.0473},
  url             = {http://arxiv.org/abs/1409.0473},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BahdanauCB14},
  keywords        = {attention, additive attention},
  timestamp       = {20181201T1029}
}

@Article{bahdanau2017-learning,
  author          = {{Bahdanau}, D. and {Bosc}, T. and {Jastrz{\c e}bski}, S. and {Grefenstette}, E. and {Vincent}, P. and {Bengio}, Y.},
  title           = {{Learning To Compute Word Embeddings on the Fly}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.00286},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Computation and Language},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{baity-jesi2018-comparing,
  author          = {{Baity-Jesi}, M. and {Sagun}, L. and {Geiger}, M. and {Spigler}, S. and {Ben Arous}, G. and {Cammarota}, C. and
                  {LeCun}, Y. and {Wyart}, M. and {Biroli}, G.},
  title           = {{Comparing Dynamics: Deep Neural Networks Versus Glassy Systems}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = mar,
  eprint          = {1803.06969},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180306969B},
  archiveprefix   = "arXiv",
  keywords        = {theory, glassy, dynamics, loss landscape},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{baldassi2007-efficient,
  author          = {Baldassi, Carlo and Braunstein, Alfredo and Brunel, Nicolas and Zecchina, Riccardo},
  title           = {Efficient Supervised Learning in Networks With Binary Synapses},
  journaltitle    = {BMC Neuroscience},
  year            = 2007,
  volume          = 8,
  number          = 2,
  pages           = 1,
  journal         = {BMC Neuroscience},
  keywords        = {physics, quantization, binary},
  publisher       = {BioMed Central},
  timestamp       = {20181201T1029}
}

@Article{baldassi2009-generalization,
  author          = {Baldassi, Carlo},
  title           = {Generalization Learning in a Perceptron With Binary Synapses},
  journaltitle    = {Journal of Statistical Physics},
  year            = 2009,
  volume          = 136,
  number          = 5,
  pages           = {902--916},
  journal         = {Journal of Statistical Physics},
  keywords        = {physics, quantization, binary},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@Article{baldassi2015-max,
  author          = {Baldassi, Carlo and Braunstein, Alfredo},
  title           = {A Max-Sum Algorithm for Training Discrete Neural Networks},
  journaltitle    = {Journal of Statistical Mechanics: Theory and Experiment},
  year            = 2015,
  volume          = 2015,
  number          = 8,
  pages           = {P08008},
  journal         = {Journal of Statistical Mechanics: Theory and Experiment},
  keywords        = {quantization, training},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1029}
}

@Article{baldassi2015-subdominant,
  author          = {Baldassi, Carlo and Ingrosso, Alessandro and Lucibello, Carlo and Saglietti, Luca and Zecchina, Riccardo},
  title           = {Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks With
                  Discrete Synapses},
  journaltitle    = {Physical review letters},
  year            = 2015,
  volume          = 115,
  number          = 12,
  pages           = 128101,
  journal         = {Physical review letters},
  publisher       = {APS},
  timestamp       = {20181201T1029}
}

@Article{baldassi2016-learning,
  author          = {Baldassi, Carlo and Gerace, Federica and Lucibello, Carlo and Saglietti, Luca and Zecchina, Riccardo},
  title           = {Learning May Need Only a Few Bits of Synaptic Precision},
  journaltitle    = {Physical Review E},
  year            = 2016,
  volume          = 93,
  number          = 5,
  pages           = 052313,
  journal         = {Physical Review E},
  keywords        = {quantization, physics},
  publisher       = {APS},
  timestamp       = {20181201T1029}
}

@Article{baldassi2016-local,
  author          = {Baldassi, Carlo and Ingrosso, Alessandro and Lucibello, Carlo and Saglietti, Luca and Zecchina, Riccardo},
  title           = {Local Entropy As a Measure for Sampling Solutions in Constraint Satisfaction Problems},
  journaltitle    = {Journal of Statistical Mechanics: Theory and Experiment},
  year            = 2016,
  volume          = 2016,
  number          = 2,
  pages           = 023301,
  journal         = {Journal of Statistical Mechanics: Theory and Experiment},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1029}
}

@Article{baldassi2016-unreasonable,
  author          = {Baldassi, Carlo and Borgs, Christian and Chayes, Jennifer T and Ingrosso, Alessandro and Lucibello, Carlo and
                  Saglietti, Luca and Zecchina, Riccardo},
  title           = {Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles To Basic
                  Algorithmic Schemes},
  journaltitle    = {Proceedings of the National Academy of Sciences},
  year            = 2016,
  volume          = 113,
  number          = 48,
  pages           = {E7655--E7662},
  journal         = {Proceedings of the National Academy of Sciences},
  publisher       = {National Acad Sciences},
  timestamp       = {20181201T1029}
}

@InProceedings{baldi1988-linear,
  author          = {Baldi, Pierre},
  title           = {Linear Learning: Landscapes and Algorithms.},
  year            = 1988,
  booktitle       = {NIPS},
  pages           = {65--72},
  timestamp       = {20181201T1029}
}

@Article{baldi1989-neural,
  author          = {Baldi, Pierre and Hornik, Kurt},
  title           = {Neural Networks and Principal Component Analysis: Learning From Examples Without Local Minima},
  journaltitle    = {Neural networks},
  year            = 1989,
  volume          = 2,
  number          = 1,
  pages           = {53--58},
  journal         = {Neural networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{baldi2012-complex,
  author          = {Baldi, Pierre and Lu, Zhiqin},
  title           = {Complex-Valued Autoencoders},
  journaltitle    = {Neural Networks},
  year            = 2012,
  volume          = 33,
  pages           = {136--147},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{baldi2016-learning,
  author          = {{Baldi}, P. and {Sadowski}, P. and {Lu}, Z.},
  title           = {{Learning in the Machine: Random Backpropagation and the Learning Channel}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = dec,
  eprint          = {1612.02734},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary
                  Computing},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@InCollection{baldi2018-neuronal,
  author          = {Baldi, Pierre and Vershynin, Roman},
  title           = {On Neuronal Capacity},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {7740--7749},
  url             = {http://papers.nips.cc/paper/7999-on-neuronal-capacity.pdf},
  timestamp       = {20181224T1342}
}

@Article{baluja2017-adversarial,
  author          = {Shumeet Baluja and Ian Fischer},
  title           = {Adversarial Transformation Networks: Learning To Generate Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.09387},
  url             = {http://arxiv.org/abs/1703.09387},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BalujaF17},
  keywords        = {adversarial, generator, atn},
  timestamp       = {20181201T1029}
}

@InCollection{baluja2017-hiding,
  author          = {Baluja, Shumeet},
  title           = {Hiding Images in Plain Sight: Deep Steganography},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2066--2076},
  url             = {http://papers.nips.cc/paper/6802-hiding-images-in-plain-sight-deep-steganography.pdf},
  timestamp       = {20181201T1029}
}

@Article{banerjee2005-clustering,
  author          = {Banerjee, Arindam and Dhillon, Inderjit S and Ghosh, Joydeep and Sra, Suvrit},
  title           = {Clustering on the Unit Hypersphere Using Von Mises-Fisher Distributions},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2005,
  volume          = 6,
  number          = {Sep},
  pages           = {1345--1382},
  journal         = {Journal of Machine Learning Research},
  timestamp       = {20181201T1029}
}

@InProceedings{bansal2018-pixelnn,
  author          = {Aayush Bansal and Yaser Sheikh and Deva Ramanan},
  title           = {Pixel{NN}: Example-based Image Synthesis},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=Syhr6pxCW},
  timestamp       = {20181201T1029}
}

@Article{bao2018-mitigation,
  author          = {{Bao}, Z. and {Mu{\~n}oz-Gonz{\'a}lez}, L. and {Lupu}, E.~C.},
  title           = {{Mitigation of Adversarial Attacks Through Embedded Feature Selection}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.05705},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180805705B},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "cs.CR",
  timestamp       = {20181201T1029}
}

@Book{barber2012-bayesian,
  author          = {Barber, David},
  title           = {Bayesian reasoning and machine learning},
  year            = 2012,
  publisher       = {Cambridge University Press},
  timestamp       = {20181201T1029}
}

@Article{barratt2018-note,
  author          = {Barratt, Shane and Sharma, Rishi},
  title           = {A Note on the Inception Score},
  journaltitle    = {arXiv preprint arXiv:1801.01973},
  year            = 2018,
  journal         = {arXiv preprint arXiv:1801.01973},
  keywords        = {gan, inception score, is},
  timestamp       = {20181201T1029}
}

@InProceedings{barreno2006-can,
  author          = {Barreno, Marco and Nelson, Blaine and Sears, Russell and Joseph, Anthony D and Tygar, J Doug},
  title           = {Can machine learning be secure?},
  year            = 2006,
  booktitle       = {Proceedings of the 2006 ACM Symposium on Information, computer and communications security},
  organization    = {ACM},
  pages           = {16--25},
  timestamp       = {20181201T1029}
}

@Article{barron1994-performance,
  author          = {Barron, John L and Fleet, David J and Beauchemin, Steven S},
  title           = {Performance of Optical Flow Techniques},
  journaltitle    = {International journal of computer vision},
  year            = 1994,
  volume          = 12,
  number          = 1,
  pages           = {43--77},
  journal         = {International journal of computer vision},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@InProceedings{bartal2011-dimensionality,
  author          = {Bartal, Yair and Recht, Ben and Schulman, Leonard J},
  title           = {Dimensionality reduction: beyond the Johnson-Lindenstrauss bound},
  year            = 2011,
  booktitle       = {Proceedings of the twenty-second annual ACM-SIAM symposium on Discrete Algorithms},
  organization    = {Society for Industrial and Applied Mathematics},
  pages           = {868--887},
  timestamp       = {20181201T1029}
}

@Article{battaglia2018-relational,
  author          = {{Battaglia}, P.~W. and {Hamrick}, J.~B. and {Bapst}, V. and {Sanchez-Gonzalez}, A. and {Zambaldi}, V. and {Malinowski},
                  M. and {Tacchetti}, A. and {Raposo}, D. and {Santoro}, A. and {Faulkner}, R. and {Gulcehre}, C. and {Song}, F. and
                  {Ballard}, A. and {Gilmer}, J. and {Dahl}, G. and {Vaswani}, A. and {Allen}, K. and {Nash}, C. and {Langston}, V. and
                  {Dyer}, C. and {Heess}, N. and {Wierstra}, D. and {Kohli}, P. and {Botvinick}, M. and {Vinyals}, O. and {Li}, Y. and
                  {Pascanu}, R.},
  title           = {{Relational Inductive Biases, Deep Learning, and Graph networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jun,
  eprint          = {1806.01261},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180601261B},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning},
  timestamp       = {20181201T1029}
}

@Article{battiti1995-training,
  author          = {Battiti, Roberto and Tecchiolli, Giampietro},
  title           = {Training Neural Nets With the Reactive Tabu Search},
  journaltitle    = {IEEE transactions on neural networks},
  year            = 1995,
  volume          = 6,
  number          = 5,
  pages           = {1185--1200},
  journal         = {IEEE transactions on neural networks},
  publisher       = {IEEE},
  timestamp       = {20181201T1029}
}

@Article{bau2017-network,
  author          = {David Bau and Bolei Zhou and Aditya Khosla and Aude Oliva and Antonio Torralba},
  title           = {Network Dissection: Quantifying Interpretability of Deep Visual Representations},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.05796},
  journal         = {CoRR},
  keywords        = {intrepret, cnn},
  timestamp       = {20181201T1029}
}

@InProceedings{bau2019-visualizing,
  author          = {David Bau and Jun-Yan Zhu and Hendrik Strobelt and Bolei Zhou and Joshua B. Tenenbaum and William T. Freeman and
                  Antonio Torralba},
  title           = {Visualizing and Understanding Generative Adversarial Networks},
  year            = 2019,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=Hyg_X2C5FX},
  timestamp       = {20190427T1338}
}

@InProceedings{baxter2000-direct,
  author          = {Baxter, Jonathan and Bartlett, Peter L},
  title           = {Direct gradient-based reinforcement learning},
  year            = 2000,
  booktitle       = {Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on},
  volume          = 3,
  organization    = {IEEE},
  pages           = {271--274},
  timestamp       = {20181201T1029}
}

@Article{bayer2014-learning,
  author          = {{Bayer}, J. and {Osendorfer}, C.},
  title           = {{Learning Stochastic Recurrent Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = nov,
  eprint          = {1411.7610},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{beattie2016-deepmind,
  author          = {Charles Beattie and Joel Z. Leibo and Denis Teplyashin and Tom Ward and Marcus Wainwright and Heinrich K{\"{u}}ttler
                  and Andrew Lefrancq and Simon Green and V{\'{\i}}ctor Vald{\'{e}}s and Amir Sadik and Julian Schrittwieser and Keith
                  Anderson and Sarah York and Max Cant and Adam Cain and Adrian Bolton and Stephen Gaffney and Helen King and Demis Hassabis
                  and Shane Legg and Stig Petersen},
  title           = {Deepmind Lab},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.03801},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@Article{belinkov2017-synthetic,
  author          = {Yonatan Belinkov and Yonatan Bisk},
  title           = {Synthetic and Natural Noise Both Break Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.02173},
  journal         = {CoRR},
  keywords        = {adversarial, char cnn, nmt},
  timestamp       = {20181201T1029}
}

@Article{bell1995-information,
  author          = {Bell, Anthony J and Sejnowski, Terrence J},
  title           = {An Information-Maximization Approach To Blind Separation and Blind Deconvolution},
  journaltitle    = {Neural computation},
  year            = 1995,
  volume          = 7,
  number          = 6,
  pages           = {1129--1159},
  journal         = {Neural computation},
  publisher       = {MIT Press},
  timestamp       = {20181201T1029}
}

@InProceedings{bellec2018-deep,
  author          = {Guillaume Bellec and David Kappel and Wolfgang Maass and Robert Legenstein},
  title           = {Deep Rewiring: Training very sparse deep networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BJ_wN01C-},
  timestamp       = {20181201T1029}
}

@Article{bellemare2013-arcade,
  author          = {Bellemare, Marc G and Naddaf, Yavar and Veness, Joel and Bowling, Michael},
  title           = {The Arcade Learning Environment: an Evaluation Platform for General Agents},
  journaltitle    = {Journal of Artificial Intelligence Research},
  year            = 2013,
  volume          = 47,
  pages           = {253--279},
  journal         = {Journal of Artificial Intelligence Research},
  keywords        = {rl},
  timestamp       = {20181201T1011}
}

@Article{bellemare2017-cramer,
  author          = {{Bellemare}, M.~G. and {Danihelka}, I. and {Dabney}, W. and {Mohamed}, S. and {Lakshminarayanan}, B. and {Hoyer},
                  S. and {Munos}, R.},
  title           = {{The Cramer Distance As a Solution To Biased Wasserstein Gradients}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.10743},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{bellemare2017-distributional,
  author          = {{Bellemare}, M.~G. and {Dabney}, W. and {Munos}, R.},
  title           = {{A Distributional Perspective on Reinforcement Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.06887},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{bendor2012-biasing,
  author          = {Bendor, Daniel and Wilson, Matthew A},
  title           = {Biasing the Content of Hippocampal Replay During Sleep},
  journaltitle    = {Nature neuroscience},
  year            = 2012,
  volume          = 15,
  number          = 10,
  pages           = {1439--1444},
  journal         = {Nature neuroscience},
  publisher       = {Nature Publishing Group},
  timestamp       = {20181201T1029}
}

@Online{benenson2013-what,
  author          = {Rodrigo Benenson},
  title           = {What is the class of this image?},
  year            = 2013,
  url             = {http://rodrigob.github.io/are_we_there_yet/build/classification_datasets_results.html},
  note            = "[Online; accessed 2016-02-23]",
  urldate         = {2016-02-23},
  timestamp       = {20181201T1029}
}

@Book{bengio1990-learning,
  author          = {Bengio, Yoshua and Bengio, Samy and Cloutier, Jocelyn},
  title           = {Learning a synaptic learning rule},
  year            = 1990,
  publisher       = {Universit{\'e} de Montr{\'e}al, D{\'e}partement d'informatique et de recherche op{\'e}rationnelle},
  keywords        = {meta learning},
  timestamp       = {20181201T1029}
}

@Article{bengio1994-learning,
  author          = {Y. Bengio and P. Simard and P. Frasconi},
  title           = {Learning Long-Term Dependencies With Gradient Descent Is Difficult},
  journaltitle    = {IEEE Transactions on Neural Networks},
  year            = 1994,
  volume          = 5,
  number          = 2,
  month           = {Mar},
  pages           = {157-166},
  issn            = {1045-9227},
  doi             = {10.1109/72.279181},
  url             = {https://doi.org/10.1109/72.279181},
  journal         = {IEEE Transactions on Neural Networks},
  timestamp       = {20181201T1029}
}

@Article{bengio2003-neural,
  author          = {Bengio, Yoshua and Ducharme, R{\'e}jean and Vincent, Pascal and Jauvin, Christian},
  title           = {A Neural Probabilistic Language Model},
  journaltitle    = {Journal of machine learning research},
  year            = 2003,
  volume          = 3,
  number          = {Feb},
  pages           = {1137--1155},
  journal         = {Journal of machine learning research},
  keywords        = {word2vec},
  timestamp       = {20181201T1029}
}

@InProceedings{bengio2006-convex,
  author          = {Bengio, Yoshua and Roux, Nicolas L and Vincent, Pascal and Delalleau, Olivier and Marcotte, Patrice},
  title           = {Convex neural networks},
  year            = 2006,
  booktitle       = {Advances in neural information processing systems},
  pages           = {123--130},
  timestamp       = {20181201T1029}
}

@InCollection{bengio2006-curse,
  author          = {Bengio, Yoshua and Olivier Delalleau and Nicolas L. Roux},
  title           = {The Curse of Highly Variable Functions for Local Kernel Machines},
  year            = 2006,
  booktitle       = {Advances in Neural Information Processing Systems 18},
  editor          = {Y. Weiss and B. Sch{\"o}lkopf and J. C. Platt},
  publisher       = {MIT Press},
  pages           = {107--114},
  url             = {http://papers.nips.cc/paper/2810-the-curse-of-highly-variable-functions-for-local-kernel-machines.pdf},
  timestamp       = {20181201T1029}
}

@Article{bengio2007-greedy,
  author          = {Bengio, Yoshua and Lamblin, Pascal and Popovici, Dan and Larochelle, Hugo and others},
  title           = {Greedy Layer-Wise Training of Deep Networks},
  journaltitle    = {Advances in neural information processing systems},
  year            = 2007,
  volume          = 19,
  pages           = 153,
  journal         = {Advances in neural information processing systems},
  publisher       = {MIT; 1998},
  timestamp       = {20181201T1029}
}

@InProceedings{bengio2009-curriculum,
  author          = {Bengio, Yoshua and Louradour, J{\'e}r{\^o}me and Collobert, Ronan and Weston, Jason},
  title           = {Curriculum Learning},
  year            = 2009,
  booktitle       = {Proceedings of the 26th Annual International Conference on Machine Learning},
  series          = {ICML '09},
  publisher       = {ACM},
  location        = {Montreal, Quebec, Canada},
  isbn            = {978-1-60558-516-1},
  pages           = {41--48},
  doi             = {10.1145/1553374.1553380},
  url             = {https://doi.org/10.1145/1553374.1553380},
  acmid           = 1553380,
  address         = {New York, NY, USA},
  numpages        = 8,
  timestamp       = {20181201T1029}
}

@Article{bengio2009-learning,
  author          = {Bengio, Yoshua},
  title           = {Learning Deep Architectures for Ai},
  journaltitle    = {Found. Trends Mach. Learn.},
  year            = 2009,
  volume          = 2,
  number          = 1,
  month           = jan,
  pages           = {1--127},
  issn            = {1935-8237},
  doi             = {10.1561/2200000006},
  url             = {https://doi.org/10.1561/2200000006},
  journal         = {Found. Trends Mach. Learn.},
  acmid           = 1658424,
  address         = {Hanover, MA, USA},
  issue_date      = {January 2009},
  numpages        = 127,
  publisher       = {Now Publishers Inc.},
  timestamp       = {20181201T1029}
}

@Article{bengio2012-better,
  author          = {Yoshua Bengio and Gr{\'e}goire Mesnil and Yann Dauphin and Salah Rifai},
  title           = {Better Mixing Via Deep Representations},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1207.4404},
  url             = {http://arxiv.org/abs/1207.4404},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1207-4404},
  timestamp       = {20181201T1029}
}

@Article{bengio2012-practical,
  author          = {Yoshua Bengio},
  title           = {Practical Recommendations for Gradient-Based Training of Deep Architectures},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1206.5533},
  url             = {http://arxiv.org/abs/1206.5533},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1206-5533},
  timestamp       = {20181201T1029}
}

@Article{bengio2012-representation,
  author          = {Yoshua Bengio and Aaron C. Courville and Pascal Vincent},
  title           = {Representation Learning: {A} Review and New Perspectives},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1206.5538},
  url             = {http://arxiv.org/abs/1206.5538},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1206-5538},
  timestamp       = {20181201T1029}
}

@Article{bengio2013-estimating,
  author          = {Yoshua Bengio and Nicholas L{\'e}onard and Aaron C. Courville},
  title           = {Estimating Or Propagating Gradients Through Stochastic Neurons for Conditional Computation},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1308.3432},
  url             = {http://arxiv.org/abs/1308.3432},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BengioLC13},
  keywords        = {dynamic},
  timestamp       = {20181201T1029}
}

@Article{bengio2013-generalized,
  author          = {Yoshua Bengio and Li Yao and Guillaume Alain and Pascal Vincent},
  title           = {Generalized Denoising Auto-Encoders As Generative Models},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1305.6663},
  url             = {http://arxiv.org/abs/1305.6663},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1305-6663},
  timestamp       = {20181201T1029}
}

@Article{bengio2014-how,
  author          = {Yoshua Bengio},
  title           = {How Auto-Encoders Could Provide Credit Assignment in Deep Networks Via Target Propagation},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1407.7906},
  url             = {http://arxiv.org/abs/1407.7906},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Bengio14},
  timestamp       = {20181201T1029}
}

@Article{bengio2015-conditional,
  author          = {Emmanuel Bengio and Pierre{-}Luc Bacon and Joelle Pineau and Doina Precup},
  title           = {Conditional Computation in Neural Networks for Faster Models},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06297},
  journal         = {CoRR},
  keywords        = {dynamic},
  timestamp       = {20181201T1029}
}

@Article{bengio2015-early,
  author          = {Bengio, Yoshua and Fischer, Asja},
  title           = {Early Inference in Energy-Based Models Approximates Back-Propagation},
  journaltitle    = {arXiv preprint arXiv:1510.02777},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1510.02777},
  timestamp       = {20181201T1029}
}

@InCollection{bengio2015-scheduled,
  author          = {Bengio, Samy and Vinyals, Oriol and Jaitly, Navdeep and Shazeer, Noam},
  title           = {Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1171--1179},
  url             = {http://papers.nips.cc/paper/5956-scheduled-sampling-for-sequence-prediction-with-recurrent-neural-networks.pdf},
  keywords        = {exposure bias, scheduled sampling, rnn},
  timestamp       = {20181201T1029}
}

@Article{bengio2015-stdp,
  author          = {Bengio, Yoshua and Mesnard, Thomas and Fischer, Asja and Zhang, Saizheng and Wu, Yuhuai},
  title           = {Stdp As Presynaptic Activity Times Rate of Change of Postsynaptic Activity},
  journaltitle    = {arXiv preprint arXiv:1509.05936},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1509.05936},
  timestamp       = {20181201T1029}
}

@Article{bengio2017-consciousness,
  author          = {Bengio, Yoshua},
  title           = {The Consciousness Prior},
  journaltitle    = {arXiv preprint arXiv:1709.08568},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1709.08568},
  timestamp       = {20181201T1029}
}

@Article{bengio2017-independently,
  author          = {{Bengio}, E. and {Thomas}, V. and {Pineau}, J. and {Precup}, D. and {Bengio}, Y.},
  title           = {{Independently Controllable Features}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.07718},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{bengio2017-stdp,
  author          = {Bengio, Y and Mesnard, T and Fischer, A and Zhang, S and Wu, Y},
  title           = {Stdp As Presynaptic Activity Times Rate of Change of Postsynaptic Activity Approximates Back-Propagation},
  journaltitle    = {Neural Computation},
  year            = 2017,
  volume          = 10,
  journal         = {Neural Computation},
  timestamp       = {20181201T1029}
}

@InCollection{berglund2015-bidirectional,
  author          = {Berglund, Mathias and Raiko, Tapani and Honkala, Mikko and K{\"a}rkk{\"a}inen, Leo and Vetek, Akos and Karhunen, Juha
                  T},
  title           = {Bidirectional Recurrent Neural Networks as Generative Models},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {856--864},
  url             = {http://papers.nips.cc/paper/5651-bidirectional-recurrent-neural-networks-as-generative-models.pdf},
  timestamp       = {20181201T1029}
}

@InCollection{bergstra2011-algorithms,
  author          = {James S. Bergstra and Bardenet, R{\'e}mi and Bengio, Yoshua and Bal{\'a}zs K{\'e}gl},
  title           = {Algorithms for Hyper-Parameter Optimization},
  year            = 2011,
  booktitle       = {Advances in Neural Information Processing Systems 24},
  editor          = {J. Shawe-Taylor and R.S. Zemel and P.L. Bartlett and F. Pereira and K.Q. Weinberger},
  publisher       = {Curran Associates, Inc.},
  pages           = {2546--2554},
  url             = {http://papers.nips.cc/paper/4443-algorithms-for-hyper-parameter-optimization.pdf},
  timestamp       = {20181201T1029}
}

@Article{bergstra2012-random,
  author          = {Bergstra, James and Bengio, Yoshua},
  title           = {Random Search for Hyper-Parameter Optimization},
  journaltitle    = {J. Mach. Learn. Res.},
  year            = 2012,
  volume          = 13,
  number          = 1,
  month           = feb,
  pages           = {281--305},
  issn            = {1532-4435},
  url             = {http://dl.acm.org/citation.cfm?id=2503308.2188395},
  journal         = {J. Mach. Learn. Res.},
  acmid           = 2188395,
  issue_date      = {January 2012},
  keywords        = {deep learning, global optimization, model selection, neural networks, response surface modeling},
  numpages        = 25,
  publisher       = {JMLR.org},
  timestamp       = {20181201T1029}
}

@InProceedings{berka2013-evolving,
  author          = {Berka, Tobias and Mayer, Helmut A},
  title           = {Evolving artificial neural networks for nonlinear feature construction},
  year            = 2013,
  booktitle       = {Proceedings of the 15th annual conference on Genetic and evolutionary computation},
  organization    = {ACM},
  pages           = {1037--1044},
  timestamp       = {20181201T1029}
}

@Article{berthelot2017-began,
  author          = {{Berthelot}, D. and {Schumm}, T. and {Metz}, L.},
  title           = {{BEGAN: Boundary Equilibrium Generative Adversarial Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.10717},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@InProceedings{beyer1999-when,
  author          = {Beyer, Kevin and Goldstein, Jonathan and Ramakrishnan, Raghu and Shaft, Uri},
  title           = {When is "nearest neighbor" meaningful?},
  year            = 1999,
  booktitle       = {International conference on database theory},
  organization    = {Springer},
  pages           = {217--235},
  timestamp       = {20181201T1029}
}

@Article{bhatnagar2009-natural,
  author          = {Bhatnagar, Shalabh and Sutton, Richard S and Ghavamzadeh, Mohammad and Lee, Mark},
  title           = {Natural Actor--critic Algorithms},
  journaltitle    = {Automatica},
  year            = 2009,
  volume          = 45,
  number          = 11,
  pages           = {2471--2482},
  journal         = {Automatica},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{biederman1987-recognition,
  author          = {Biederman, Irving},
  title           = {Recognition-By-Components: a Theory of Human Image Understanding.},
  keywords        = {rbc},
  journaltitle    = {Psychological review},
  year            = 1987,
  volume          = 94,
  number          = 2,
  pages           = 115,
  journal         = {Psychological review},
  publisher       = {American Psychological Association},
  timestamp       = {20181225T1011}
}

@InCollection{bietti2017-invariance,
  author          = {Bietti, Alberto and Mairal, Julien},
  title           = {Invariance and Stability of Deep Convolutional Representations},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6211--6221},
  url             = {http://papers.nips.cc/paper/7201-invariance-and-stability-of-deep-convolutional-representations.pdf},
  timestamp       = {20181201T1029}
}

@InProceedings{biggio2010-multiple,
  author          = {Biggio, Battista and Fumera, Giorgio and Roli, Fabio},
  title           = {Multiple classifier systems under attack},
  year            = 2010,
  booktitle       = {International Workshop on Multiple Classifier Systems},
  organization    = {Springer},
  pages           = {74--83},
  timestamp       = {20181201T1029}
}

@Article{biggio2011-support,
  author          = {Biggio, Battista and Nelson, Blaine and Laskov, Pavel},
  title           = {Support Vector Machines Under Adversarial Label Noise.},
  journaltitle    = {ACML},
  year            = 2011,
  volume          = 20,
  pages           = {97--112},
  journal         = {ACML},
  timestamp       = {20181201T1029}
}

@InProceedings{biggio2013-evasion,
  author          = {Biggio, Battista and Corona, Igino and Maiorca, Davide and Nelson, Blaine and {\v{S}}rndi{\'c}, Nedim and Laskov, Pavel
                  and Giacinto, Giorgio and Roli, Fabio},
  title           = {Evasion attacks against machine learning at test time},
  year            = 2013,
  booktitle       = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
  organization    = {Springer},
  pages           = {387--402},
  timestamp       = {20181201T1029}
}

@Article{biggio2014-pattern,
  author          = {Biggio, Battista and Fumera, Giorgio and Roli, Fabio},
  title           = {Pattern Recognition Systems Under Attack: Design Issues and Research Challenges},
  journaltitle    = {International Journal of Pattern Recognition and Artificial Intelligence},
  year            = 2014,
  volume          = 28,
  number          = 07,
  pages           = 1460002,
  journal         = {International Journal of Pattern Recognition and Artificial Intelligence},
  publisher       = {World Scientific},
  timestamp       = {20181201T1029}
}

@Article{biggio2014-security,
  author          = {Biggio, Battista and Fumera, Giorgio and Roli, Fabio},
  title           = {Security Evaluation of Pattern Classifiers Under Attack},
  journaltitle    = {IEEE transactions on knowledge and data engineering},
  year            = 2014,
  volume          = 26,
  number          = 4,
  pages           = {984--996},
  journal         = {IEEE transactions on knowledge and data engineering},
  publisher       = {IEEE},
  timestamp       = {20181201T1029}
}

@Book{bird2009-natural,
  author          = {Bird, Steven and Klein, Ewan and Loper, Edward},
  title           = {Natural language processing with Python: analyzing text with the natural language toolkit},
  year            = 2009,
  publisher       = {" O'Reilly Media, Inc."},
  keywords        = {nltk},
  timestamp       = {20181201T1029}
}

@Book{bishop2006-pattern,
  author          = {Bishop, Christopher M},
  title           = {Pattern Recognition and Machine Learning},
  year            = 2006,
  editor          = {M. Jordan and J. Kleinberg and B. Sch{\"o}lkopf},
  keywords        = {prml},
  timestamp       = {20181201T1029}
}

@Article{blaser2016-random,
  author          = {Rico Blaser and Piotr Fryzlewicz},
  title           = {Random Rotation Ensembles},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2016,
  volume          = 17,
  number          = 4,
  pages           = {1-26},
  url             = {http://jmlr.org/papers/v17/blaser16a.html},
  journal         = {Journal of Machine Learning Research},
  timestamp       = {20181201T1029}
}

@Article{blum1992-training,
  author          = {Blum, Avrim L and Rivest, Ronald L},
  title           = {Training a 3-node Neural Network Is Np-Complete},
  journaltitle    = {Neural Networks},
  year            = 1992,
  volume          = 5,
  number          = 1,
  pages           = {117--127},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{blum2006-random,
  author          = {Blum, Avrim},
  title           = {Random Projection, Margins, Kernels, and Feature-Selection},
  journaltitle    = {Lecture notes in computer science},
  year            = 2006,
  volume          = 3940,
  pages           = 52,
  journal         = {Lecture notes in computer science},
  keywords        = {random},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@InCollection{blum2015-variational,
  author          = {Blum, Avrim and Haghtalab, Nika and Procaccia, Ariel D},
  title           = {Variational Dropout and the Local Reparameterization Trick},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2575--2583},
  url             = {http://papers.nips.cc/paper/5666-variational-dropout-and-the-local-reparameterization-trick.pdf},
  timestamp       = {20181201T1029}
}

@Article{blundell2015-weight,
  author          = {{Blundell}, C. and {Cornebise}, J. and {Kavukcuoglu}, K. and {Wierstra}, D.},
  title           = {{Weight Uncertainty in Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = may,
  eprint          = {1505.05424},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {compression, regularizer, variational},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{blundell2016-model,
  author          = {Blundell, Charles and Uria, Benigno and Pritzel, Alexander and Li, Yazhe and Ruderman, Avraham and Leibo, Joel Z and
                  Rae, Jack and Wierstra, Daan and Hassabis, Demis},
  title           = {Model-Free Episodic Control},
  journaltitle    = {arXiv preprint arXiv:1606.04460},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1606.04460},
  keywords        = {episodic memory},
  timestamp       = {20181201T1029}
}

@Article{bojanowski2016-enriching,
  author          = {Piotr Bojanowski and Edouard Grave and Armand Joulin and Tomas Mikolov},
  title           = {Enriching Word Vectors With Subword Information},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1607.04606},
  url             = {http://arxiv.org/abs/1607.04606},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BojanowskiGJM16},
  timestamp       = {20181201T1029}
}

@Article{bojanowski2017-optimizing,
  author          = {{Bojanowski}, P. and {Joulin}, A. and {Lopez-Paz}, D. and {Szlam}, A.},
  title           = {{Optimizing the Latent Space of Generative Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.05776},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{bojanowski2017-unsupervised,
  author          = {{Bojanowski}, P. and {Joulin}, A.},
  title           = {{Unsupervised Learning By Predicting Noise}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = apr,
  eprint          = {1704.05310},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{bojarski2016-end,
  author          = {Mariusz Bojarski and Davide Del Testa and Daniel Dworakowski and Bernhard Firner and Beat Flepp and Prasoon Goyal and
                  Lawrence D. Jackel and Mathew Monfort and Urs Muller and Jiakai Zhang and Xin Zhang and Jake Zhao and Karol Zieba},
  title           = {End To End Learning for Self-Driving Cars},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.07316},
  eprint          = {1604.07316},
  url             = {http://arxiv.org/abs/1604.07316},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/BojarskiTDFFGJM16},
  keywords        = {dave2},
  timestamp       = {20181201T1029}
}

@Article{bolukbasi2017-adaptive,
  author          = {Tolga Bolukbasi and Joseph Wang and Ofer Dekel and Venkatesh Saligrama},
  title           = {Adaptive Neural Networks for Fast Test-Time Prediction},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1702.07811},
  journal         = {CoRR},
  keywords        = {dynamic},
  timestamp       = {20181201T1029}
}

@Article{bora2017-compressed,
  author          = {{Bora}, A. and {Jalal}, A. and {Price}, E. and {Dimakis}, A.~G.},
  title           = {{Compressed Sensing Using Generative Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.03208},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Information Theory, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{bordes2018-iteratively,
  author          = {Bordes, Florian and Berthier, Tess and Di Jorio, Lisa and Vincent, Pascal and Bengio, Yoshua},
  title           = {Iteratively Unveiling New Regions of Interest in Deep Learning Models},
  journaltitle    = {MIDL},
  year            = 2018,
  journal         = {MIDL},
  keywords        = {interpret, roi, saliency map},
  timestamp       = {20181201T1029}
}

@InCollection{borgs2017-thy,
  author          = {Borgs, Christian and Chayes, Jennifer and Lee, Christina E. and Shah, Devavrat},
  title           = {Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4718--4729},
  url             = {http://papers.nips.cc/paper/7057-thy-friend-is-my-friend-iterative-collaborative-filtering-for-sparse-matrix-estimation.pdf},
  timestamp       = {20181201T1029}
}

@Book{borwein2010-convex,
  author          = {Borwein, Jonathan M and Vanderwerff, Jon D},
  title           = {Convex functions: constructions, characterizations and counterexamples},
  year            = 2010,
  volume          = 109,
  publisher       = {Cambridge University Press Cambridge},
  timestamp       = {20181201T1029}
}

@Article{bottou2016-optimization,
  author          = {{Bottou}, L. and {Curtis}, F.~E. and {Nocedal}, J.},
  title           = {{Optimization Methods for Large-Scale Machine Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.04838},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Mathematics - Optimization and Control},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{botvinick2009-hierarchically,
  author          = {Botvinick, Matthew M and Niv, Yael and Barto, Andrew C},
  title           = {Hierarchically Organized Behavior and Its Neural Foundations: a Reinforcement Learning Perspective},
  journaltitle    = {Cognition},
  year            = 2009,
  volume          = 113,
  number          = 3,
  pages           = {262--280},
  journal         = {Cognition},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{botvinick2012-hierarchical,
  author          = "Matthew Michael Botvinick",
  title           = {Hierarchical Reinforcement Learning and Decision Making},
  journaltitle    = "Current Opinion in Neurobiology",
  year            = 2012,
  volume          = 22,
  number          = 6,
  pages           = "956 - 962",
  note            = "Decision making",
  issn            = "0959-4388",
  doi             = "https://doi.org/10.1016/j.conb.2012.05.008",
  url             = {https://doi.org/https://doi.org/10.1016/j.conb.2012.05.008},
  journal         = "Current Opinion in Neurobiology",
  timestamp       = {20181201T1029}
}

@Article{bousquet2017-critical,
  author          = {{Bousquet}, O. and {Gelly}, S. and {Kurach}, K. and {Teytaud}, O. and {Vincent}, D.},
  title           = {{Critical Hyper-Parameters: No Random, No Cry}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.03200},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{bousquet2017-from,
  author          = {{Bousquet}, O. and {Gelly}, S. and {Tolstikhin}, I. and {Simon-Gabriel}, C.-J. and {Schoelkopf}, B.},
  title           = {{From Optimal Transport To Generative Modeling: the Vegan cookbook}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.07642},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{bowman2015-generating,
  author          = {Samuel R. Bowman and Luke Vilnis and Oriol Vinyals and Andrew M. Dai and Rafal J{\'o}zefowicz and Samy Bengio},
  title           = {Generating Sentences From a Continuous Space},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06349},
  url             = {http://arxiv.org/abs/1511.06349},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BowmanVVDJB15},
  timestamp       = {20181201T1029}
}

@Article{bowman2015-large,
  author          = {Bowman, Samuel R and Angeli, Gabor and Potts, Christopher and Manning, Christopher D},
  title           = {A Large Annotated Corpus for Learning Natural Language Inference},
  journaltitle    = {arXiv preprint arXiv:1508.05326},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1508.05326},
  keywords        = {data, snli},
  timestamp       = {20181201T1029}
}

@Book{boyd2004-convex,
  author          = {Boyd, Stephen and Vandenberghe, Lieven},
  title           = {Convex optimization},
  year            = 2004,
  publisher       = {Cambridge university press},
  timestamp       = {20181201T1029}
}

@Article{bradbury2016-quasi,
  author          = {James Bradbury and Stephen Merity and Caiming Xiong and Richard Socher},
  title           = {Quasi-Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.01576},
  url             = {http://arxiv.org/abs/1611.01576},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BradburyMXS16},
  keywords        = {quasi,lstm,speedup,qrnn},
  timestamp       = {20181201T1029}
}

@Article{bradshaw2017-adversarial,
  author          = {Bradshaw, John and Matthews, Alexander G de G and Ghahramani, Zoubin},
  title           = {Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks},
  journaltitle    = {arXiv preprint arXiv:1707.02476},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.02476},
  keywords        = {gaussian process, adversarial, gpdnn, rbf, domain shift},
  timestamp       = {20181201T1029}
}

@Article{brakel2017-learning,
  author          = {Brakel, Philemon and Bengio, Yoshua},
  title           = {Learning Independent Features With Adversarial Nets for Non-Linear Ica},
  journaltitle    = {arXiv preprint arXiv:1710.05050},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1710.05050},
  timestamp       = {20181201T1029}
}

@Article{braunstein2006-learning,
  author          = {Braunstein, Alfredo and Zecchina, Riccardo},
  title           = {Learning By Message Passing in Networks of Discrete Synapses},
  journaltitle    = {Physical review letters},
  year            = 2006,
  volume          = 96,
  number          = 3,
  pages           = 030201,
  journal         = {Physical review letters},
  keywords        = {physics, quantization, training, binary},
  publisher       = {APS},
  timestamp       = {20181201T1029}
}

@Article{bray2007-statistics,
  author          = {{Bray}, A.~J. and {Dean}, D.~S.},
  title           = {{Statistics of Critical Points of Gaussian Fields on Large-Dimensional Spaces}},
  journaltitle    = {Physical Review Letters},
  year            = 2007,
  volume          = 98,
  number          = 15,
  eid             = 150201,
  month           = apr,
  pages           = 150201,
  doi             = {10.1103/PhysRevLett.98.150201},
  eprint          = {cond-mat/0611023},
  url             = {https://doi.org/10.1103/PhysRevLett.98.150201},
  journal         = {Physical Review Letters},
  keywords        = {Probability theory stochastic processes and statistics, Statistical models},
  timestamp       = {20181201T1029}
}

@Article{brazinskas2016-embedding,
  author          = {Arthur Brazinskas and Serhii Havrylov and Ivan Titov},
  title           = {Embedding Words As Distributions With a Bayesian Skip-Gram Model},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1711.11027},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@Article{breiman2001-random,
  author          = "Breiman, Leo",
  title           = {Random Forests},
  journaltitle    = "Machine Learning",
  year            = 2001,
  volume          = 45,
  number          = 1,
  month           = "Oct",
  pages           = "5--32",
  issn            = "1573-0565",
  doi             = "10.1023/A:1010933404324",
  url             = {https://doi.org/10.1023/A:1010933404324},
  journal         = "Machine Learning",
  day             = 01,
  timestamp       = {20181201T1029}
}

@InProceedings{brendel2019-approximating,
  author          = {Wieland Brendel and Matthias Bethge},
  title           = {Approximating {CNN}s with Bag-of-local-Features models works surprisingly well on ImageNet},
  year            = 2019,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SkfMWhAqYQ},
  timestamp       = {20190211T0914}
}

@Article{breuleux2011-quickly,
  author          = {Breuleux, Olivier and Bengio, Yoshua and Vincent, Pascal},
  title           = {Quickly Generating Representative Samples From an Rbm-Derived Process},
  journaltitle    = {Neural Computation},
  year            = 2011,
  volume          = 23,
  number          = 8,
  pages           = {2058--2073},
  journal         = {Neural Computation},
  publisher       = {MIT Press},
  timestamp       = {20181201T1029}
}

@Article{britz2017-massive,
  author          = {Britz, Denny and Goldie, Anna and Luong, Thang and Le, Quoc},
  title           = {Massive Exploration of Neural Machine Translation Architectures},
  journaltitle    = {arXiv preprint arXiv:1703.03906},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1703.03906},
  keywords        = {nmt, attention},
  timestamp       = {20181201T1029}
}

@InProceedings{brock2019-large,
  author          = {Andrew Brock and Jeff Donahue and Karen Simonyan},
  title           = {Large Scale {GAN} Training for High Fidelity Natural Image Synthesis},
  keywords        = {gan, biggan},
  year            = 2019,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=B1xsqj09Fm},
  timestamp       = {20190424T0757}
}

@Article{brocki2007-kohonen,
  author          = {Brocki, {\L}ukasz and Kor{\v{z}}inek, Danijel},
  title           = {Kohonen Self-Organizing Map for the Traveling Salesperson Problem},
  journaltitle    = {Recent Advances in Mechatronics},
  year            = 2007,
  pages           = {116--119},
  journal         = {Recent Advances in Mechatronics},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@Article{bromley1993-signature,
  author          = {Bromley, Jane and Bentz, James W. and Bottou, L{\'e}on and Guyon, Isabelle and Lecun, Yann and Moore, Cliff and
                  S{\"a}ckinger, Eduard and Shah, Roopak},
  title           = {Signature Verification Using a "Siamese" Time Delay Neural Network},
  journaltitle    = {International Journal of Pattern Recognition and Artificial Intelligence},
  year            = 1993,
  volume          = 07,
  number          = 04,
  pages           = {669-688},
  doi             = {10.1142/S0218001493000339},
  eprint          = {http://www.worldscientific.com/doi/pdf/10.1142/S0218001493000339},
  url             = {https://doi.org/10.1142/S0218001493000339},
  journal         = {International Journal of Pattern Recognition and Artificial Intelligence},
  timestamp       = {20181201T1029}
}

@Article{bronstein2016-geometric,
  author          = {Bronstein, Michael M and Bruna, Joan and LeCun, Yann and Szlam, Arthur and Vandergheynst, Pierre},
  title           = {Geometric Deep Learning: Going Beyond Euclidean Data},
  journaltitle    = {arXiv preprint arXiv:1611.08097},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1611.08097},
  timestamp       = {20181201T1029}
}

@Article{brown2017-adversarial,
  author          = {{Brown}, T.~B. and {Man{\'e}}, D. and {Roy}, A. and {Abadi}, M. and {Gilmer}, J.},
  title           = {{Adversarial Patch}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.09665},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171209665B},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, patch},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1029}
}

@Article{brueckner2012-static,
  author          = {Br{\"u}ckner, Michael and Kanzow, Christian and Scheffer, Tobias},
  title           = {Static Prediction Games for Adversarial Learning Problems},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2012,
  volume          = 13,
  number          = {Sep},
  pages           = {2617--2654},
  journal         = {Journal of Machine Learning Research},
  timestamp       = {20181201T1029}
}

@InProceedings{bruna2011-classification,
  author          = {Bruna, Joan and Mallat, St{\'e}phane},
  title           = {Classification with scattering operators},
  year            = 2011,
  booktitle       = {Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on},
  organization    = {IEEE},
  pages           = {1561--1566},
  timestamp       = {20181201T1029}
}

@Article{brundage2015-modeling,
  author          = {Miles Brundage},
  title           = {Modeling Progress in {AI}},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.05849},
  url             = {http://arxiv.org/abs/1512.05849},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Brundage15},
  timestamp       = {20181201T1029}
}

@Article{brunel2004-optimal,
  author          = "Nicolas Brunel and Vincent Hakim and Philippe Isope and Jean-Pierre Nadal and Boris Barbour",
  title           = {Optimal Information Storage and the Distribution of Synaptic Weights: Perceptron Versus Purkinje Cell},
  journaltitle    = "Neuron",
  year            = 2004,
  volume          = 43,
  number          = 5,
  pages           = "745 - 757",
  issn            = "0896-6273",
  doi             = {10.1016/j.neuron.2004.08.023},
  url             = {https://doi.org/10.1016/j.neuron.2004.08.023},
  journal         = "Neuron",
  timestamp       = {20181201T1029}
}

@Article{bruni2014-multimodal,
  author          = {Bruni, Elia and Tran, Nam-Khanh and Baroni, Marco},
  title           = {Multimodal Distributional Semantics},
  journaltitle    = {Journal of Artificial Intelligence Research},
  year            = 2014,
  volume          = 49,
  pages           = {1--47},
  journal         = {Journal of Artificial Intelligence Research},
  keywords        = {men, bless},
  timestamp       = {20181201T1029}
}

@InProceedings{brutzkus2018-sgd,
  author          = {Alon Brutzkus and Amir Globerson and Eran Malach and Shai Shalev-Shwartz},
  title           = {{SGD} Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=rJ33wwxRb},
  timestamp       = {20181201T1029}
}

@Article{bubeck2014-convex,
  author          = {{Bubeck}, S.},
  title           = {{Convex Optimization: Algorithms and Complexity}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = may,
  eprint          = {1405.4980},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Mathematics - Optimization and Control, Computer Science - Computational Complexity, Computer Science - Learning,
                  Computer Science - Numerical Analysis, Statistics - Machine Learning},
  primaryclass    = "math.OC",
  timestamp       = {20181201T1029}
}

@Article{bubeck2015-geometric,
  author          = {Bubeck, S{\'e}bastien and Lee, Yin Tat and Singh, Mohit},
  title           = {A Geometric Alternative To Nesterov's Accelerated Gradient Descent},
  journaltitle    = {arXiv preprint arXiv:1506.08187},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1506.08187},
  timestamp       = {20181201T1029}
}

@InProceedings{bucila2006-model,
  author          = {Cristian Bucila and Rich Caruana and Alexandru Niculescu{-}Mizil},
  title           = {Model compression},
  year            = 2006,
  booktitle       = {Proceedings of the Twelfth {ACM} {SIGKDD} International Conference on Knowledge Discovery and Data Mining,
                  Philadelphia, PA, USA, August 20-23, 2006},
  pages           = {535--541},
  doi             = {10.1145/1150402.1150464},
  url             = {https://doi.org/10.1145/1150402.1150464},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/conf/kdd/BucilaCN06},
  timestamp       = {20181201T1029}
}

@Article{burda2015-importance,
  author          = {Yuri Burda and Roger B. Grosse and Ruslan Salakhutdinov},
  title           = {Importance Weighted Autoencoders},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1509.00519},
  url             = {http://arxiv.org/abs/1509.00519},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/BurdaGS15},
  timestamp       = {20181201T1029}
}

@InProceedings{burges2005-learning,
  author          = {Burges, Chris and Shaked, Tal and Renshaw, Erin and Lazier, Ari and Deeds, Matt and Hamilton, Nicole and Hullender,
                  Greg},
  title           = {Learning to rank using gradient descent},
  year            = 2005,
  booktitle       = {Proceedings of the 22nd international conference on Machine learning},
  organization    = {ACM},
  pages           = {89--96},
  keywords        = {learning to rank},
  timestamp       = {20181201T1029}
}

@Article{burton1987-color,
  author          = {Burton, GJ and Moorhead, Ian R},
  title           = {Color and Spatial Structure in Natural Scenes},
  journaltitle    = {Applied Optics},
  year            = 1987,
  volume          = 26,
  number          = 1,
  pages           = {157--170},
  journal         = {Applied Optics},
  publisher       = {Optical Society of America},
  timestamp       = {20181201T1029}
}

@Book{busoniu2010-reinforcement,
  author          = {Busoniu, Lucian and Babuska, Robert and De Schutter, Bart and Ernst, Damien},
  title           = {Reinforcement learning and dynamic programming using function approximators},
  year            = 2010,
  volume          = 39,
  publisher       = {CRC press},
  timestamp       = {20181201T1029}
}

@Article{cai2016-making,
  author          = {Cai, Jonathon and Shin, Richard and Song, Dawn},
  title           = {Making Neural Programming Architectures Generalize Via Recursion},
  journaltitle    = {arXiv preprint arXiv:1610.05755},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1610.05755},
  timestamp       = {20181201T1029}
}

@Article{cai2017-comprehensive,
  author          = {HongYun Cai and Vincent W. Zheng and Kevin Chen{-}Chuan Chang},
  title           = {A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1709.07604},
  eprint          = {1709.07604},
  url             = {http://arxiv.org/abs/1709.07604},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1709-07604},
  keywords        = {embedding, graph, survey},
  timestamp       = {20181201T1029}
}

@Misc{cai2017-making,
  author          = {Cai, Jonathon and Shin, Richard and Song, Dawn},
  title           = {Making Neural Programming Architectures Generalize Via Recursion},
  year            = 2017,
  timestamp       = {20181201T1029}
}

@Book{callahan2010-advanced,
  author          = {Callahan, James J},
  title           = {Advanced calculus: a geometric view},
  year            = 2010,
  publisher       = {Springer Science \& Business Media},
  timestamp       = {20181201T1029}
}

@InProceedings{cao2007-learning,
  author          = {Cao, Zhe and Qin, Tao and Liu, Tie-Yan and Tsai, Ming-Feng and Li, Hang},
  title           = {Learning to rank: from pairwise approach to listwise approach},
  year            = 2007,
  booktitle       = {Proceedings of the 24th international conference on Machine learning},
  organization    = {ACM},
  pages           = {129--136},
  keywords        = {learning to rank, listnet, listwise},
  timestamp       = {20181201T1029}
}

@InProceedings{cao2017-cw2vec,
  author          = {Cao, Shaosheng and Lu, Wei and Zhou, Jun and Li, Xiaolong},
  title           = {Cw2vec: Learning Chinese Word Embeddings with stroke n-grams},
  year            = 2017,
  booktitle       = {Proceedings of the 32th AAAI Conference on Artificial Intelligence},
  organization    = {AAAI},
  keywords        = {cw2vec},
  timestamp       = {20181201T1029}
}

@Article{carlini2016-towards,
  author          = {Nicholas Carlini and David Wagner},
  title           = {Towards Evaluating the Robustness of Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1608.04644},
  url             = {http://arxiv.org/abs/1608.04644},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/CarliniW16a},
  keywords        = {adversarial, attack, cw},
  timestamp       = {20181201T1029}
}

@Article{carlini2017-adversarial,
  author          = {{Carlini}, N. and {Wagner}, D.},
  title           = {{Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.07263},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{carlini2018-audio,
  author          = {{Carlini}, N. and {Wagner}, D.},
  title           = {{Audio Adversarial Examples: Targeted Attacks on Speech-To-Text}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.01944},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180101944C},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, audio, speech},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@InCollection{carlson2015-preconditioned,
  author          = {Carlson, David E and Collins, Edo and Hsieh, Ya-Ping and Carin, Lawrence and Cevher, Volkan},
  title           = {Preconditioned Spectral Descent for Deep Learning},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2971--2979},
  url             = {http://papers.nips.cc/paper/5795-preconditioned-spectral-descent-for-deep-learning.pdf},
  timestamp       = {20181201T1029}
}

@Misc{carreira-perpinan2005-contrastive,
  author          = {Miguel A. Carreira-Perpinan and Geoffrey E. Hinton},
  title           = {On Contrastive Divergence Learning},
  year            = 2005,
  timestamp       = {20181201T1029}
}

@InProceedings{carreira-perpinan2014-distributed,
  author          = {Carreira-Perpinan, Miguel and Wang, Weiran},
  title           = {Distributed optimization of deeply nested systems},
  year            = 2014,
  booktitle       = {Artificial Intelligence and Statistics},
  pages           = {10--19},
  timestamp       = {20181201T1029}
}

@InCollection{carreira-perpinan2015,
  author          = {Carreira-Perpinan, Miguel A. and Vladymyrov, Max},
  title           = {A fast, universal algorithm to learn parametric nonlinear embeddings},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {253--261},
  url             = {http://papers.nips.cc/paper/5972-a-fast-universal-algorithm-to-learn-parametric-nonlinear-embeddings.pdf},
  timestamp       = {20181201T1029}
}

@InProceedings{carreira-perpinan2015-hashing,
  author          = {Carreira-Perpin{\'a}n, Miguel A and Raziperchikolaei, Ramin},
  title           = {Hashing with binary autoencoders},
  year            = 2015,
  booktitle       = {Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on},
  organization    = {IEEE},
  pages           = {557--566},
  keywords        = {hashing, binary},
  timestamp       = {20181201T1029}
}

@Article{carreira-perpinan2017-model,
  author          = {{Carreira-Perpi{\~n}{\'a}n}, M.~{\'A}. and {Idelbayev}, Y.},
  title           = {{Model Compression As Constrained Optimization, With Application To Neural Nets}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.04319},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {survey, compression, quantization},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{carter2016-experiments,
  author          = {Carter, Shan and Ha, David and Johnson, Ian and Olah, Chris},
  title           = {Experiments in Handwriting With a Neural Network},
  journaltitle    = {Distill},
  year            = 2016,
  doi             = {10.23915/distill.00004},
  url             = {https://doi.org/10.23915/distill.00004},
  journal         = {Distill},
  timestamp       = {20181201T1029}
}

@InCollection{caruana1998-multitask,
  author          = {Caruana, Rich},
  title           = {Multitask learning},
  year            = 1998,
  booktitle       = {Learning to learn},
  publisher       = {Springer},
  pages           = {95--133},
  timestamp       = {20181201T1029}
}

@Article{castellani2005-spin,
  author          = {Castellani, Tommaso and Cavagna, Andrea},
  title           = {Spin-Glass Theory for Pedestrians},
  journaltitle    = {Journal of Statistical Mechanics: Theory and Experiment},
  year            = 2005,
  volume          = 2005,
  number          = 05,
  pages           = {P05012},
  journal         = {Journal of Statistical Mechanics: Theory and Experiment},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1029}
}

@Article{castillo2000-g,
  author          = {Castillo, Pedro A and Merelo, JJ and Prieto, Alberto and Rivas, V and Romero, Gustavo},
  title           = {G-Prop: Global Optimization of Multilayer Perceptrons Using Gas},
  journaltitle    = {Neurocomputing},
  year            = 2000,
  volume          = 35,
  number          = 1,
  pages           = {149--163},
  journal         = {Neurocomputing},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{cer2018-universal,
  author          = {Daniel Cer and Yinfei Yang and Sheng{-}yi Kong and Nan Hua and Nicole Limtiaco and Rhomni St. John and Noah Constant
                  and Mario Guajardo{-}Cespedes and Steve Yuan and Chris Tar and Yun{-}Hsuan Sung and Brian Strope and Ray Kurzweil},
  title           = {Universal Sentence Encoder},
  keywords        = {embedding, sentence},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1803.11175},
  eprint          = {1803.11175},
  url             = {http://arxiv.org/abs/1803.11175},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1803-11175},
  timestamp       = {20190103T1618}
}

@Article{chai2017-low,
  author          = {Sek Chai and Aswin Raghavan and David C. Zhang and Mohamed R. Amer and Timothy J. Shields},
  title           = {Low Precision Neural Networks Using Subband Decomposition},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.08595},
  journal         = {CoRR},
  keywords        = {quantization},
  timestamp       = {20181201T1029}
}

@Article{chalupka2014-visual,
  author          = {{Chalupka}, K. and {Perona}, P. and {Eberhardt}, F.},
  title           = {{Visual Causal Feature Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = dec,
  eprint          = {1412.2309},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and
                  Pattern Recognition, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{chan2018-everybody,
  author          = {Chan, Caroline and Ginosar, Shiry and Zhou, Tinghui and Efros, Alexei A},
  title           = {Everybody Dance Now},
  journaltitle    = {arXiv preprint arXiv:1808.07371},
  year            = 2018,
  journal         = {arXiv preprint arXiv:1808.07371}
}

@Book{chandler1987-introduction,
  author          = {Chandler, David},
  title           = {Introduction to modern statistical mechanics},
  year            = 1987,
  publisher       = {Oxford University Press},
  isbn            = 9780195042771,
  pages           = 288,
  timestamp       = {20181201T1029}
}

@Article{chang2015-shapenet,
  author          = {Angel X. Chang and Thomas A. Funkhouser and Leonidas J. Guibas and Pat Hanrahan and Qi{-}Xing Huang and Zimo Li and
                  Silvio Savarese and Manolis Savva and Shuran Song and Hao Su and Jianxiong Xiao and Li Yi and Fisher Yu},
  title           = {Shapenet: an Information-Rich 3d Model Repository},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.03012},
  eprint          = {1512.03012},
  url             = {http://arxiv.org/abs/1512.03012},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/ChangFGHHLSSSSX15},
  keywords        = {shapenet, shapenetcore},
  timestamp       = {20181201T1029}
}

@Article{chang2017-code,
  author          = {Chang, Le and Tsao, Doris Y.},
  title           = {The Code for Facial Identity in the Primate Brain},
  journaltitle    = {Cell},
  year            = 2017,
  volume          = 169,
  number          = 6,
  month           = 06,
  pages           = {1013-1028.e14},
  issn            = {0092-8674},
  doi             = {10.1016/j.cell.2017.05.011},
  url             = {https://doi.org/10.1016/j.cell.2017.05.011},
  journal         = {Cell},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{chang2018-neural,
  author          = {{Chang}, O. and {Lipson}, H.},
  title           = {{Neural Network Quine}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = mar,
  eprint          = {1803.05859},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180305859C},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1029}
}

@Article{charbonneau2014-fractal,
  author          = {Charbonneau, Patrick and Kurchan, Jorge and Parisi, Giorgio and Urbani, Pierfrancesco and Zamponi, Francesco},
  title           = {Fractal Free Energy Landscapes in Structural Glasses},
  journaltitle    = {Nature communications},
  year            = 2014,
  volume          = 5,
  journal         = {Nature communications},
  publisher       = {Nature Publishing Group},
  timestamp       = {20181201T1029}
}

@InProceedings{charikar2002-similarity,
  author          = {Charikar, Moses S},
  title           = {Similarity estimation techniques from rounding algorithms},
  year            = 2002,
  booktitle       = {Proceedings of the thiry-fourth annual ACM symposium on Theory of computing},
  organization    = {ACM},
  pages           = {380--388},
  timestamp       = {20181201T1029}
}

@Article{chatfield2014-return,
  author          = {Ken Chatfield and Karen Simonyan and Andrea Vedaldi and Andrew Zisserman},
  title           = {Return of the Devil in the Details: Delving Deep Into Convolutional Nets},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1405.3531},
  url             = {http://arxiv.org/abs/1405.3531},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChatfieldSVZ14},
  timestamp       = {20181201T1029}
}

@Article{chattopadhyay2014-data,
  author          = {Ishanu Chattopadhyay and Hod Lipson},
  title           = {Data Smashing},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1401.0742},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@Article{chaudhari2016-entropy,
  author          = {Pratik Chaudhari and Anna Choromanska and Stefano Soatto and Yann LeCun},
  title           = {Entropy-Sgd: Biasing Gradient Descent Into Wide Valleys},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.01838},
  url             = {http://arxiv.org/abs/1611.01838},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChaudhariCSL16},
  timestamp       = {20181201T1029}
}

@Article{chaudhari2017-stochastic,
  author          = {{Chaudhari}, P. and {Soatto}, S.},
  title           = {{Stochastic Gradient Descent Performs Variational Inference, Converges To Limit Cycles for Deep networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.11029},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171011029C},
  archiveprefix   = "arXiv",
  keywords        = {sgd, minima, variational inference},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{che2016-mode,
  author          = {Che, Tong and Li, Yanran and Jacob, Athul Paul and Bengio, Yoshua and Li, Wenjie},
  title           = {Mode Regularized Generative Adversarial Networks},
  journaltitle    = {arXiv preprint arXiv:1612.02136},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1612.02136},
  timestamp       = {20181201T1029}
}

@Article{chelba2017-n,
  author          = {Ciprian Chelba and Mohammad Norouzi and Samy Bengio},
  title           = {N-Gram Language Modeling Using Recurrent Neural Network Estimation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.10724},
  eprint          = {1703.10724},
  url             = {http://arxiv.org/abs/1703.10724},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/ChelbaNB17},
  timestamp       = {20190109T1413}
}

@Article{chen1997-neural,
  author          = {Yan Qiu Chen and R. I. Damper and M. S. Nixon},
  title           = {On Neural-Network Implementations of K-Nearest Neighbor Pattern Classifiers},
  journaltitle    = {IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications},
  year            = 1997,
  volume          = 44,
  number          = 7,
  month           = {Jul},
  pages           = {622-629},
  issn            = {1057-7122},
  doi             = {10.1109/81.596943},
  url             = {https://doi.org/10.1109/81.596943},
  journal         = {IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications},
  timestamp       = {20181201T1029}
}

@InCollection{chen2002-continuous,
  author          = {Chen, Hsin and Murray, Alan},
  title           = {A Continuous Restricted Boltzmann Machine with a Hardware-Amenable Learning Algorithm},
  year            = 2002,
  booktitle       = {Artificial Neural Networks -- ICANN 2002},
  language        = {English},
  volume          = 2415,
  series          = {Lecture Notes in Computer Science},
  publisher       = {Springer Berlin Heidelberg},
  isbn            = {978-3-540-44074-1},
  pages           = {358-363},
  doi             = {10.1007/3-540-46084-5_58},
  url             = {https://doi.org/10.1007/3-540-46084-5_58},
  timestamp       = {20181201T1029}
}

@InProceedings{chen2014-fast,
  author          = {Chen, Danqi and Manning, Christopher},
  title           = {A Fast and Accurate Dependency Parser Using Neural Networks},
  keywords        = {nlp, dependency},
  year            = 2014,
  booktitle       = {Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
  pages           = {740--750},
  timestamp       = {20181230T1057}
}

@Article{chen2014-introduction,
  author          = {Chen, Tianqi},
  title           = {Introduction To Boosted Trees},
  journaltitle    = {University of Washing Computer Science. University of Washington},
  year            = 2014,
  volume          = 22,
  journal         = {University of Washing Computer Science. University of Washington},
  timestamp       = {20181201T1029}
}

@Article{chen2014-split,
  author          = {Chen, Xueying and Xie, Min-ge},
  title           = {A Split-And-Conquer Approach for Analysis of Extraordinarily Large Data},
  journaltitle    = {Statistica Sinica},
  year            = 2014,
  pages           = {1655--1684},
  journal         = {Statistica Sinica},
  publisher       = {JSTOR},
  timestamp       = {20181201T1029}
}

@Article{chen2015-compressing,
  author          = {Chen, Wenlin and Wilson, James T and Tyree, Stephen and Weinberger, Kilian Q and Chen, Yixin},
  title           = {Compressing Neural Networks With the Hashing Trick},
  journaltitle    = {CoRR, abs/1504.04788},
  year            = 2015,
  journal         = {CoRR, abs/1504.04788},
  keywords        = {quantization, hashing, hashnet},
  timestamp       = {20181201T1029}
}

@InProceedings{chen2015-higgs,
  author          = {Chen, Tianqi and He, Tong},
  title           = {Higgs boson discovery with boosted trees},
  year            = 2015,
  booktitle       = {JMLR: Workshop and Conference Proceedings},
  number          = 42,
  pages           = {69--80},
  timestamp       = {20181201T1029}
}

@Article{chen2015-net2net,
  author          = {{Chen}, T. and {Goodfellow}, I. and {Shlens}, J.},
  title           = {{Net2Net: Accelerating Learning Via Knowledge Transfer}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = nov,
  eprint          = {1511.05641},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{chen2016-human,
  author          = {Ching{-}Hang Chen and Deva Ramanan},
  title           = {3d Human Pose Estimation = 2d Pose Estimation + Matching},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.06524},
  eprint          = {1612.06524},
  url             = {http://arxiv.org/abs/1612.06524},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/ChenR16a},
  timestamp       = {20181215T0727}
}

@Article{chen2016-infogan,
  author          = {Xi Chen and Yan Duan and Rein Houthooft and John Schulman and Ilya Sutskever and Pieter Abbeel},
  title           = {Infogan: Interpretable Representation Learning By Information Maximizing Generative Adversarial Nets},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.03657},
  url             = {http://arxiv.org/abs/1606.03657},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChenDHSSA16},
  timestamp       = {20181201T1029}
}

@Article{chen2017-dual,
  author          = {{Chen}, Y. and {Li}, J. and {Xiao}, H. and {Jin}, X. and {Yan}, S. and {Feng}, J.},
  title           = {{Dual Path Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.01629},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1029}
}

@Article{chen2017-ead,
  author          = {{Chen}, P.-Y. and {Sharma}, Y. and {Zhang}, H. and {Yi}, J. and {Hsieh}, C.-J.},
  title           = {{EAD: Elastic-Net Attacks To Deep Neural Networks Via Adversarial Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = sep,
  eprint          = {1709.04114},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv170904114C},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{chen2017-photographic,
  author          = {{Chen}, Q. and {Koltun}, V.},
  title           = {{Photographic Image Synthesis With Cascaded Refinement Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.09405},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {generator, realistic, cascaded refinement networks, crn},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1029}
}

@Article{chen2018-deeplab,
  author          = {Chen, Liang-Chieh and Papandreou, George and Kokkinos, Iasonas and Murphy, Kevin and Yuille, Alan L},
  title           = {Deeplab: Semantic Image Segmentation With Deep Convolutional Nets, Atrous Convolution, and Fully Connected Crfs},
  journaltitle    = {IEEE transactions on pattern analysis and machine intelligence},
  year            = 2018,
  volume          = 40,
  number          = 4,
  pages           = {834--848},
  journal         = {IEEE transactions on pattern analysis and machine intelligence},
  keywords        = {data, deeplab},
  publisher       = {IEEE},
  timestamp       = {20181201T1029}
}

@Article{chen2018-learning,
  author          = {Jianbo Chen and Le Song and Martin J. Wainwright and Michael I. Jordan},
  title           = {Learning To Explain: an Information-Theoretic Perspective on Model Interpretation},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1802.07814},
  eprint          = {1802.07814},
  url             = {http://arxiv.org/abs/1802.07814},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1802-07814},
  timestamp       = {20181224T0934}
}

@InCollection{chen2018-neural,
  author          = {Chen, Tian Qi and Rubanova, Yulia and Bettencourt, Jesse and Duvenaud, David K},
  title           = {Neural Ordinary Differential Equations},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6572--6583},
  url             = {http://papers.nips.cc/paper/7892-neural-ordinary-differential-equations.pdf},
  timestamp       = {20181224T1335}
}

@Article{cheney2016-topological,
  author          = {Cheney, Nick and Lipson, Hod},
  title           = {Topological Evolution for Embodied Cellular Automata},
  journaltitle    = {Theoretical Computer Science},
  year            = 2016,
  volume          = 633,
  pages           = {19--27},
  journal         = {Theoretical Computer Science},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{cheney2017-robustness,
  author          = {Nicholas Cheney and Martin Schrimpf and Gabriel Kreiman},
  title           = {On the Robustness of Convolutional Neural Networks To Internal Architecture and Weight Perturbations},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.08245},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@Article{cheng2015-training,
  author          = {Cheng, Zhiyong and Soudry, Daniel and Mao, Zexi and Lan, Zhenzhong},
  title           = {Training Binary Multilayer Neural Networks for Image Classification Using Expectation Backpropagation},
  journaltitle    = {arXiv preprint arXiv:1503.03562},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1503.03562},
  keywords        = {quantization, binary, expectation backpropagation},
  timestamp       = {20181201T1029}
}

@Article{cheng2018-seq2sick,
  author          = {Minhao Cheng and Jinfeng Yi and Huan Zhang and Pin{-}Yu Chen and Cho{-}Jui Hsieh},
  title           = {Seq2sick: Evaluating the Robustness of Sequence-To-Sequence Models With Adversarial Examples},
  keywords        = {adversarial, text},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1803.01128},
  eprint          = {1803.01128},
  url             = {http://arxiv.org/abs/1803.01128},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1803-01128},
  timestamp       = {20181227T1520}
}

@InProceedings{chentanez2004-intrinsically,
  author          = {Chentanez, Nuttapong and Barto, Andrew G and Singh, Satinder P},
  title           = {Intrinsically motivated reinforcement learning},
  year            = 2004,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1281--1288},
  timestamp       = {20181201T1029}
}

@InCollection{chierichetti2017-fair,
  author          = {Chierichetti, Flavio and Kumar, Ravi and Lattanzi, Silvio and Vassilvitskii, Sergei},
  title           = {Fair Clustering Through Fairlets},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5036--5044},
  url             = {http://papers.nips.cc/paper/7088-fair-clustering-through-fairlets.pdf},
  timestamp       = {20181201T1029}
}

@InCollection{cho2011-improved,
  author          = {Cho, KyungHyun and Ilin, Alexander and Raiko, Tapani},
  title           = {Improved Learning of Gaussian-Bernoulli Restricted Boltzmann Machines},
  year            = 2011,
  booktitle       = {Artificial Neural Networks and Machine Learning -- ICANN 2011},
  editor          = {Honkela, Timo and Duch, W\l{}odzis\l{}aw and Girolami, Mark and Kaski, Samuel},
  language        = {English},
  volume          = 6791,
  series          = {Lecture Notes in Computer Science},
  publisher       = {Springer Berlin Heidelberg},
  isbn            = {978-3-642-21734-0},
  pages           = {10-17},
  doi             = {10.1007/978-3-642-21735-7_2},
  url             = {https://doi.org/10.1007/978-3-642-21735-7_2},
  keywords        = {Restricted Boltzmann Machine; Gaussian-Bernoulli Restricted Boltzmann Machine; Adaptive Learning Rate; Parallel
                  Tempering},
  timestamp       = {20181201T1030}
}

@Article{cho2014-learning,
  author          = {Kyunghyun Cho and Bart van Merrienboer and {\c{C}}aglar G{\"u}l{\c{c}}ehre and Fethi Bougares and Holger Schwenk and
                  Yoshua Bengio},
  title           = {Learning Phrase Representations Using {RNN} Encoder-Decoder for Statistical Machine Translation},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1406.1078},
  url             = {http://arxiv.org/abs/1406.1078},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChoMGBSB14},
  timestamp       = {20181201T1029}
}

@Article{cho2014-properties,
  author          = {KyungHyun Cho and Bart van Merrienboer and Dzmitry Bahdanau and Yoshua Bengio},
  title           = {On the Properties of Neural Machine Translation: Encoder-Decoder Approaches},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1409.1259},
  url             = {http://arxiv.org/abs/1409.1259},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChoMBB14},
  timestamp       = {20181201T1029}
}

@InCollection{cho2015-hessian,
  author          = {Cho, Minhyung and Dhir, Chandra and Lee, Jaehyung},
  title           = {Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {883--891},
  url             = {http://papers.nips.cc/paper/5664-hessian-free-optimization-for-learning-deep-multidimensional-recurrent-neural-networks.pdf},
  timestamp       = {20181201T1029}
}

@Article{choi2018-fine,
  author          = "Heeyoul Choi and Kyunghyun Cho and Yoshua Bengio",
  title           = {Fine-Grained Attention Mechanism for Neural Machine Translation},
  journaltitle    = "Neurocomputing",
  year            = 2018,
  issn            = "0925-2312",
  doi             = "https://doi.org/10.1016/j.neucom.2018.01.007",
  url             = {https://doi.org/https://doi.org/10.1016/j.neucom.2018.01.007},
  journal         = "Neurocomputing",
  keywords        = {nmt},
  timestamp       = {20181201T1029}
}

@Article{choi2018-generative,
  author          = {{Choi}, Hyunsun and {Jang}, Eric},
  title           = {{Generative Ensembles for Robust Anomaly Detection}},
  journaltitle    = {arXiv e-prints},
  year            = 2018,
  eid             = {arXiv:1810.01392},
  month           = Oct,
  pages           = {arXiv:1810.01392},
  eprint          = {1810.01392},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/#abs/2018arXiv181001392C},
  archiveprefix   = {arXiv},
  primaryclass    = {stat.ML},
  timestamp       = {20181207T1235}
}

@Misc{chollet2015-keras,
  author          = {Chollet, Fran\c{c}ois},
  title           = {Keras},
  year            = 2015,
  howpublished    = {\url{https://github.com/fchollet/keras}},
  publisher       = {GitHub},
  timestamp       = {20181201T1029}
}

@Article{choromanska2014-loss,
  author          = {{Choromanska}, A. and {Henaff}, M. and {Mathieu}, M. and {Ben Arous}, G. and {LeCun}, Y.},
  title           = {{The Loss Surfaces of Multilayer Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = nov,
  eprint          = {1412.0233},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {spin-glass, loss surface},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@InProceedings{choromanska2015-open,
  author          = {Choromanska, Anna and LeCun, Yann and Arous, G{\'e}rard Ben},
  title           = {Open Problem: The landscape of the loss surfaces of multilayer networks.},
  year            = 2015,
  booktitle       = {COLT},
  pages           = {1756--1760},
  timestamp       = {20181201T1029}
}

@Article{christiano2017-deep,
  author          = {{Christiano}, P. and {Leike}, J. and {Brown}, T.~B. and {Martic}, M. and {Legg}, S. and {Amodei}, D.},
  title           = {{Deep Reinforcement Learning From Human preferences}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.03741},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {rl, reinforcement learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{chu2017-cyclegan,
  author          = {Casey Chu and Andrey Zhmoginov and Mark Sandler},
  title           = {Cyclegan, a Master of Steganography},
  keywords        = {cyclegan},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1712.02950},
  eprint          = {1712.02950},
  url             = {http://arxiv.org/abs/1712.02950},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1712-02950},
  timestamp       = {20190102T0806}
}

@InProceedings{chua2017-neural,
  author          = {Zheng Leong Chua and Shiqi Shen and Prateek Saxena and Zhenkai Liang},
  title           = {Neural Nets Can Learn Function Type Signatures From Binaries},
  year            = 2017,
  booktitle       = {26th {USENIX} Security Symposium ({USENIX} Security 17)},
  publisher       = {{USENIX} Association},
  isbn            = {978-1-931971-40-9},
  pages           = {99--116},
  url             = {https://www.usenix.org/conference/usenixsecurity17/technical-sessions/presentation/chua},
  address         = {Vancouver, BC},
  timestamp       = {20181201T1029}
}

@Article{chung2014-empirical,
  author          = {Junyoung Chung and {\c{C}}aglar G{\"u}l{\c{c}}ehre and KyungHyun Cho and Yoshua Bengio},
  title           = {Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.3555},
  url             = {http://arxiv.org/abs/1412.3555},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChungGCB14},
  timestamp       = {20181201T1029}
}

@Article{chung2015-recurrent,
  author          = {Junyoung Chung and Kyle Kastner and Laurent Dinh and Kratarth Goel and Aaron C. Courville and Yoshua Bengio},
  title           = {A Recurrent Latent Variable Model for Sequential Data},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.02216},
  url             = {http://arxiv.org/abs/1506.02216},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ChungKDGCB15},
  timestamp       = {20181201T1029}
}

@Article{chung2016-character,
  author          = {Chung, Junyoung and Cho, Kyunghyun and Bengio, Yoshua},
  title           = {A Character-Level Decoder Without Explicit Segmentation for Neural Machine Translation},
  journaltitle    = {arXiv preprint arXiv:1603.06147},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1603.06147},
  timestamp       = {20181201T1029}
}

@Article{chung2016-hierarchical,
  author          = {{Chung}, J. and {Ahn}, S. and {Bengio}, Y.},
  title           = {{Hierarchical Multiscale Recurrent Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = sep,
  eprint          = {1609.01704},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{ciresan2010-deep,
  author          = {Dan Claudiu Ciresan and Ueli Meier and Luca Maria Gambardella and J{\"u}rgen Schmidhuber},
  title           = {Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition},
  journaltitle    = {CoRR},
  year            = 2010,
  volume          = {abs/1003.0358},
  url             = {http://arxiv.org/abs/1003.0358},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1003-0358},
  timestamp       = {20181201T1029}
}

@Article{ciresan2011-high,
  author          = {Dan C. Ciresan and Ueli Meier and Jonathan Masci and Luca Maria Gambardella and J{\"{u}}rgen Schmidhuber},
  title           = {High-Performance Neural Networks for Visual Object Classification},
  journaltitle    = {CoRR},
  year            = 2011,
  volume          = {abs/1102.0183},
  url             = {http://arxiv.org/abs/1102.0183},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1102-0183},
  timestamp       = {20181201T1029}
}

@Article{ciresan2012-multi,
  author          = {Cire{\c{s}}An, Dan and Meier, Ueli and Masci, Jonathan and Schmidhuber, J{\"u}rgen},
  title           = {Multi-Column Deep Neural Network for Traffic Sign Classification},
  journaltitle    = {Neural Networks},
  year            = 2012,
  volume          = 32,
  pages           = {333--338},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1029}
}

@Article{cisse2017-houdini,
  author          = {{Cisse}, M. and {Adi}, Y. and {Neverova}, N. and {Keshet}, J.},
  title           = {{Houdini: Fooling Deep Structured Prediction Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.05373},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, houdini},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@InProceedings{cisse2017-parseval,
  author          = {Cisse, Moustapha and Bojanowski, Piotr and Grave, Edouard and Dauphin, Yann and Usunier, Nicolas},
  title           = {Parseval networks: Improving robustness to adversarial examples},
  year            = 2017,
  booktitle       = {International Conference on Machine Learning},
  pages           = {854--863},
  keywords        = {parseval, adversarial, regularization},
  timestamp       = {20181201T1029}
}

@InCollection{clevert2015-rectified,
  author          = {Clevert, Djork-Arn{\'e} and Mayr, Andreas and Unterthiner, Thomas and Hochreiter, Sepp},
  title           = {Rectified Factor Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1855--1863},
  url             = {http://papers.nips.cc/paper/5963-rectified-factor-networks.pdf},
  timestamp       = {20181201T1029}
}

@Article{cohen2017-count,
  author          = {{Cohen}, J.~P. and {Lo}, H.~Z. and {Bengio}, Y.},
  title           = {{Count-Ception: Counting By Fully Convolutional Redundant Counting}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.08710},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1029}
}

@Article{cohn1996-active,
  author          = {David A. Cohn and Zoubin Ghahramani and Michael I. Jordan},
  title           = {Active Learning With Statistical Models},
  journaltitle    = {CoRR},
  year            = 1996,
  volume          = {cs.AI/9603104},
  url             = {http://arxiv.org/abs/cs.AI/9603104},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/cs-AI-9603104},
  timestamp       = {20181201T1029}
}

@InCollection{cole2015-chinese,
  author          = {Cole, David},
  title           = {The Chinese Room Argument},
  year            = 2015,
  booktitle       = {The Stanford Encyclopedia of Philosophy},
  editor          = {Edward N. Zalta},
  edition         = {Winter 2015},
  publisher       = {Metaphysics Research Lab, Stanford University},
  howpublished    = {\url{https://plato.stanford.edu/archives/win2015/entries/chinese-room/}},
  timestamp       = {20181201T1029}
}

@Article{collins2014-memory,
  author          = {Maxwell D. Collins and Pushmeet Kohli},
  title           = {Memory Bounded Deep Convolutional Networks},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.1442},
  journal         = {CoRR},
  keywords        = {pruning, regularizer},
  timestamp       = {20181201T1029}
}

@InProceedings{collobert2008-unified,
  author          = {Collobert, Ronan and Weston, Jason},
  title           = {A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning},
  year            = 2008,
  booktitle       = {Proceedings of the 25th International Conference on Machine Learning},
  series          = {ICML '08},
  publisher       = {ACM},
  location        = {Helsinki, Finland},
  isbn            = {978-1-60558-205-4},
  pages           = {160--167},
  doi             = {10.1145/1390156.1390177},
  url             = {https://doi.org/10.1145/1390156.1390177},
  acmid           = 1390177,
  address         = {New York, NY, USA},
  numpages        = 8,
  timestamp       = {20181201T1029}
}

@Article{conneau2016-very,
  author          = {Alexis Conneau and Holger Schwenk and Lo{\"{\i}}c Barrault and Yann LeCun},
  title           = {Very Deep Convolutional Networks for Text Classification},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.01781},
  journal         = {CoRR},
  keywords        = {nlp, charcnn},
  timestamp       = {20181201T1029}
}

@Article{conneau2018-senteval,
  author          = {Alexis Conneau and Douwe Kiela},
  title           = {Senteval: an Evaluation Toolkit for Universal Sentence Representations},
  keywords        = {embedding, sentence, senteval},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1803.05449},
  eprint          = {1803.05449},
  url             = {http://arxiv.org/abs/1803.05449},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1803-05449},
  timestamp       = {20190103T1623}
}

@Book{cormen2001-introduction,
  author          = {Cormen, Thomas H. and Stein, Clifford and Rivest, Ronald L. and Leiserson, Charles E.},
  title           = {Introduction to Algorithms},
  year            = 2001,
  edition         = {2nd},
  publisher       = {McGraw-Hill Higher Education},
  isbn            = 0070131511,
  keywords        = {clrs},
  timestamp       = {20181201T1029}
}

@Book{cormen2009-introduction,
  author          = {Cormen, Thomas H and Leiserson, Charles E and Rivest, Ronald L and Stein, Clifford},
  title           = {Introduction to algorithms},
  year            = 2009,
  edition         = 3,
  publisher       = {MIT press},
  timestamp       = {20190110T1234}
}

@InCollection{corneil2015-attractor,
  author          = {Corneil, Dane S and Gerstner, Wulfram},
  title           = {Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze\textendash like Environments},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1684--1692},
  url             = {http://papers.nips.cc/paper/5856-attractor-network-dynamics-enable-preplay-and-rapid-path-planning-in-mazelike-environments.pdf},
  timestamp       = {20181201T1029}
}

@Article{cortes1995-support,
  author          = {Cortes, Corinna and Vapnik, Vladimir},
  title           = {Support-Vector Networks},
  journaltitle    = {Machine learning},
  year            = 1995,
  volume          = 20,
  number          = 3,
  pages           = {273--297},
  journal         = {Machine learning},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@InProceedings{cortes2017-adanet,
  author          = {Corinna Cortes and Xavier Gonzalvo and Vitaly Kuznetsov and Mehryar Mohri and Scott Yang},
  title           = {{A}da{N}et: Adaptive Structural Learning of Artificial Neural Networks},
  year            = 2017,
  booktitle       = {Proceedings of the 34th International Conference on Machine Learning},
  editor          = {Doina Precup and Yee Whye Teh},
  volume          = 70,
  series          = {Proceedings of Machine Learning Research},
  publisher       = {PMLR},
  month           = {06--11 Aug},
  pages           = {874--883},
  url             = {http://proceedings.mlr.press/v70/cortes17a.html},
  address         = {International Convention Centre, Sydney, Australia},
  pdf             = {http://proceedings.mlr.press/v70/cortes17a/cortes17a.pdf},
  timestamp       = {20181201T1029}
}

@InProceedings{costa-jussa2016-character,
  author          = {Costa-juss\`{a}, Marta R.  and Fonollosa, Jos\'{e} A. R.},
  title           = {Character-based Neural Machine Translation},
  year            = 2016,
  booktitle       = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  publisher       = {Association for Computational Linguistics},
  month           = {August},
  pages           = {357--361},
  url             = {http://anthology.aclweb.org/P16-2058},
  address         = {Berlin, Germany},
  timestamp       = {20181201T1029}
}

@Article{courbariaux2014-training,
  author          = {Courbariaux, Matthieu and David, Jean-Pierre and Bengio, Yoshua},
  title           = {Training Deep Neural Networks With Low Precision Multiplications},
  journaltitle    = {arXiv preprint arXiv:1412.7024},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1412.7024},
  keywords        = {quantization, low precision},
  timestamp       = {20181201T1029}
}

@InCollection{courbariaux2015-binaryconnect,
  author          = {Courbariaux, Matthieu and Bengio, Yoshua and David, Jean-Pierre},
  title           = {BinaryConnect: Training Deep Neural Networks with binary weights during propagations},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3123--3131},
  url             = {http://papers.nips.cc/paper/5647-binaryconnect-training-deep-neural-networks-with-binary-weights-during-propagations.pdf},
  keywords        = {quantization, binary},
  timestamp       = {20181201T1029}
}

@Article{courbariaux2016-binarynet,
  author          = {Matthieu Courbariaux and Yoshua Bengio},
  title           = {Binarynet: Training Deep Neural Networks With Weights and Activations Constrained To +1 Or -1},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.02830},
  url             = {http://arxiv.org/abs/1602.02830},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/CourbariauxB16},
  keywords        = {quantization},
  timestamp       = {20181201T1029}
}

@Book{cover2012-elements,
  author          = {Cover, Thomas M and Thomas, Joy A},
  title           = {Elements of information theory},
  year            = 2012,
  publisher       = {John Wiley \& Sons},
  timestamp       = {20181218T1633}
}

@Article{crawford2016-reinforcement,
  author          = {{Crawford}, D. and {Levit}, A. and {Ghadermarzy}, N. and {Oberoi}, J.~S. and {Ronagh}, P.},
  title           = {{Reinforcement Learning Using Quantum Boltzmann Machines}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = dec,
  eprint          = {1612.05695},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Quantum Physics, Computer Science - Artificial Intelligence, Computer Science - Learning, Computer Science - Neural and
                  Evolutionary Computing, Mathematics - Optimization and Control},
  primaryclass    = "quant-ph",
  timestamp       = {20181201T1029}
}

@InProceedings{curran2002-improvements,
  author          = {Curran, James R and Moens, Marc},
  title           = {Improvements in automatic thesaurus extraction},
  year            = 2002,
  booktitle       = {Proceedings of the ACL-02 workshop on Unsupervised lexical acquisition-Volume 9},
  organization    = {Association for Computational Linguistics},
  pages           = {59--66},
  timestamp       = {20181201T1029}
}

@Article{cybenko1989-approximation,
  author          = {Cybenko, George},
  title           = {Approximation By Superpositions of a Sigmoidal Function},
  journaltitle    = {Mathematics of control, signals and systems},
  year            = 1989,
  volume          = 2,
  number          = 4,
  pages           = {303--314},
  journal         = {Mathematics of control, signals and systems},
  publisher       = {Springer},
  timestamp       = {20181201T1029}
}

@Article{czarnecki2017-sobolev,
  author          = {Wojciech Marian Czarnecki and Simon Osindero and Max Jaderberg and Grzegorz Swirszcz and Razvan Pascanu},
  title           = {Sobolev Training for Neural Networks},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.04859},
  eprint          = {1706.04859},
  url             = {http://arxiv.org/abs/1706.04859},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/CzarneckiOJSP17},
  timestamp       = {20181201T1029}
}

@InCollection{dabkowski2017-real,
  author          = {Dabkowski, Piotr and Gal, Yarin},
  title           = {Real Time Image Saliency for Black Box Classifiers},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6970--6979},
  url             = {http://papers.nips.cc/paper/7272-real-time-image-saliency-for-black-box-classifiers.pdf},
  timestamp       = {20181201T1029}
}

@InProceedings{dahl2013-large,
  author          = {Dahl, George E and Stokes, Jack W and Deng, Li and Yu, Dong},
  title           = {Large-scale malware classification using random projections and neural networks},
  year            = 2013,
  booktitle       = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  organization    = {IEEE},
  pages           = {3422--3426},
  timestamp       = {20181201T1029}
}

@InCollection{dahlgaard2017-practical,
  author          = {Dahlgaard, S\o ren and Knudsen, Mathias and Thorup, Mikkel},
  title           = {Practical Hash Functions for Similarity Estimation and Dimensionality Reduction},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6618--6628},
  url             = {http://papers.nips.cc/paper/7239-practical-hash-functions-for-similarity-estimation-and-dimensionality-reduction.pdf},
  timestamp       = {20181201T1029}
}

@Article{dai2014-generative,
  author          = {Jifeng Dai and Ying Nian Wu},
  title           = {Generative Modeling of Convolutional Neural Networks},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6296},
  url             = {http://arxiv.org/abs/1412.6296},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DaiW14},
  timestamp       = {20181201T1029}
}

@InCollection{dai2015-semi,
  author          = {Dai, Andrew M and Le, Quoc V},
  title           = {Semi-supervised Sequence Learning},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3079--3087},
  url             = {http://papers.nips.cc/paper/5949-semi-supervised-sequence-learning.pdf},
  timestamp       = {20181201T1029}
}

@Article{dai2017-towards,
  author          = {Dai, Bo and Lin, Dahua and Urtasun, Raquel and Fidler, Sanja},
  title           = {Towards Diverse and Natural Image Descriptions Via a Conditional Gan},
  journaltitle    = {arXiv preprint arXiv:1703.06029},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1703.06029},
  timestamp       = {20181201T1029}
}

@InProceedings{dalvi2004-adversarial,
  author          = {Dalvi, Nilesh and Domingos, Pedro and Sanghai, Sumit and Verma, Deepak and others},
  title           = {Adversarial classification},
  year            = 2004,
  booktitle       = {Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining},
  organization    = {ACM},
  pages           = {99--108},
  keywords        = {adversarial data},
  timestamp       = {20181201T1029}
}

@InProceedings{daniely2014-from,
  author          = {Daniely, Amit and Linial, Nati and Shalev-Shwartz, Shai},
  title           = {From average case complexity to improper learning complexity},
  year            = 2014,
  booktitle       = {Proceedings of the 46th Annual ACM Symposium on Theory of Computing},
  organization    = {ACM},
  pages           = {441--448},
  timestamp       = {20181201T1029}
}

@InProceedings{das2018-mixed,
  author          = {Dipankar Das and Naveen Mellempudi and Dheevatsa Mudigere and Dhiraj Kalamkar and Sasikanth Avancha and Kunal Banerjee
                  and Srinivas Sridharan and Karthik Vaidyanathan and Bharat Kaul and Evangelos Georganas and Alexander Heinecke and Pradeep
                  Dubey and Jesus Corbal and Nikita Shustrov and Roma Dubtsov and Evarist Fomenko and Vadim Pirogov},
  title           = {Mixed Precision Training of Convolutional Neural Networks using Integer Operations},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=H135uzZ0-},
  timestamp       = {20181201T1029}
}

@Article{dasgupta1994-power,
  author          = {DasGupta, Bhaskar and Schnitger, Georg},
  title           = {The Power of Approximating: a Comparison of Activation Functions},
  journaltitle    = {MATHEMATICAL RESEARCH},
  year            = 1994,
  volume          = 79,
  pages           = {641--641},
  journal         = {MATHEMATICAL RESEARCH},
  publisher       = {VCH VERLAGSGESELLSCHAFT},
  timestamp       = {20181201T1029}
}

@Article{dasgupta2008-introduction,
  author          = {Dasgupta, Mrinal},
  title           = {An Introduction To Quantum Field Theory},
  journaltitle    = {School of Physics and Astronomy, University of Manchester},
  year            = 2008,
  journal         = {School of Physics and Astronomy, University of Manchester},
  timestamp       = {20181201T1029}
}

@Article{dauphin2014-identifying,
  author          = {{Dauphin}, Y. and {Pascanu}, R. and {Gulcehre}, C. and {Cho}, K. and {Ganguli}, S. and {Bengio}, Y.},
  title           = {{Identifying and Attacking the Saddle Point Problem in High-Dimensional Non-Convex optimization}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = jun,
  eprint          = {1406.2572},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Mathematics - Optimization and Control, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{davenport2007-smashed,
  author          = {Davenport, Mark A and Duarte, Marco F and Wakin, Michael B and Laska, Jason N and Takhar, Dharmpal and Kelly, Kevin F
                  and Baraniuk, Richard G},
  title           = {The Smashed Filter for Compressive Classification and Target Recognition},
  journaltitle    = {Computational Imaging V at SPIE Electronic Imaging},
  year            = 2007,
  journal         = {Computational Imaging V at SPIE Electronic Imaging},
  timestamp       = {20181201T1029}
}

@InCollection{davis1989-mapping,
  author          = {Davis, Lawrence},
  title           = {Mapping Classifier Systems into Neural Networks},
  year            = 1989,
  booktitle       = {NIPS},
  editor          = {Touretzky, David S.},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  isbn            = {1-558-60015-9},
  chapter         = {Advances in Neural Information Processing Systems 1},
  pages           = {49--56},
  url             = {http://dl.acm.org/citation.cfm?id=89851.89857},
  acmid           = 89857,
  address         = {San Francisco, CA, USA},
  numpages        = 8,
  timestamp       = {20181201T1029}
}

@Article{deerwester1990-indexing,
  author          = {Deerwester, Scott and Dumais, Susan T and Furnas, George W and Landauer, Thomas K and Harshman, Richard},
  title           = {Indexing By Latent Semantic Analysis},
  journaltitle    = {Journal of the American society for information science},
  year            = 1990,
  volume          = 41,
  number          = 6,
  pages           = {391--407},
  journal         = {Journal of the American society for information science},
  publisher       = {Wiley Online Library},
  timestamp       = {20181201T1029}
}

@Article{dekker1994-kohonen,
  author          = {Dekker, Anthony H},
  title           = {Kohonen Neural Networks for Optimal Colour Quantization},
  journaltitle    = {Network: Computation in Neural Systems},
  year            = 1994,
  volume          = 5,
  number          = 3,
  pages           = {351--367},
  journal         = {Network: Computation in Neural Systems},
  publisher       = {Taylor \& Francis},
  timestamp       = {20181201T1029}
}

@Article{denil2013-predicting,
  author          = {Misha Denil and Babak Shakibi and Laurent Dinh and Marc'Aurelio Ranzato and Nando de Freitas},
  title           = {Predicting Parameters in Deep Learning},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1306.0543},
  url             = {http://arxiv.org/abs/1306.0543},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DenilSDRF13},
  keywords        = {redundency, low rank approximation},
  timestamp       = {20181201T1029}
}

@Article{denton2014-exploiting,
  author          = {Emily Denton and Wojciech Zaremba and Joan Bruna and Yann LeCun and Rob Fergus},
  title           = {Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1404.0736},
  url             = {http://arxiv.org/abs/1404.0736},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DentonZBLF14},
  keywords        = {low rank, pruning},
  timestamp       = {20181201T1029}
}

@InCollection{denton2017-unsupervised,
  author          = {Denton, Emily L and Birodkar, vighnesh},
  title           = {Unsupervised Learning of Disentangled Representations from Video},
  keywords        = {disentangle},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4417--4426},
  url             = {http://papers.nips.cc/paper/7028-unsupervised-learning-of-disentangled-representations-from-video.pdf},
  timestamp       = {20181201T1029}
}

@InCollection{desjardins2015-natural,
  author          = {Desjardins, Guillaume and Simonyan, Karen and Pascanu, Razvan and kavukcuoglu, koray},
  title           = {Natural Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2071--2079},
  url             = {http://papers.nips.cc/paper/5953-natural-neural-networks.pdf},
  timestamp       = {20181201T1029}
}

@Article{devlin2015-exploring,
  author          = {Jacob Devlin and Saurabh Gupta and Ross B. Girshick and Margaret Mitchell and C. Lawrence Zitnick},
  title           = {Exploring Nearest Neighbor Approaches for Image Captioning},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1505.04467},
  journal         = {CoRR},
  timestamp       = {20181201T1029}
}

@Article{devlin2018-bert,
  author          = {{Devlin}, J. and {Chang}, M.-W. and {Lee}, K. and {Toutanova}, K.},
  title           = {{BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = oct,
  eprint          = {1810.04805},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv181004805D},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1029}
}

@Article{devon2017-boundary,
  author          = {{Devon Hjelm}, R and {Jacob}, A.~P. and {Che}, T. and {Cho}, K. and {Bengio}, Y.},
  title           = {{Boundary-Seeking Generative Adversarial Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.08431},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{devon2018-learning,
  author          = {{Devon Hjelm}, R and {Fedorov}, A. and {Lavoie-Marchildon}, S. and {Grewal}, K. and {Trischler}, A. and {Bengio}, Y.},
  title           = {{Learning Deep Representations By Mutual Information Estimation and maximization}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.06670},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180806670D},
  archiveprefix   = "arXiv",
  keywords        = {lr, dim},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@InProceedings{diehl2016-conversion,
  author          = {Diehl, Peter U and Zarrella, Guido and Cassidy, Andrew and Pedroni, Bruno U and Neftci, Emre},
  title           = {Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware},
  year            = 2016,
  booktitle       = {Rebooting Computing (ICRC), IEEE International Conference on},
  organization    = {IEEE},
  pages           = {1--8},
  timestamp       = {20181201T1029}
}

@phdthesis{sutskever2013,
  title           = {Training recurrent neural networks},
  author          = {Sutskever, Ilya},
  year            = {2013},
  school          = {University of Toronto}
}

@Article{dieng2016-topicrnn,
  author          = {Adji B. Dieng and Chong Wang and Jianfeng Gao and John William Paisley},
  title           = {Topicrnn: {A} Recurrent Neural Network With Long-Range Semantic Dependency},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.01702},
  eprint          = {1611.01702},
  url             = {http://arxiv.org/abs/1611.01702},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/DiengWGP16},
  timestamp       = {20181201T1029}
}

@InProceedings{dietterich2000-ensemble,
  author          = {Dietterich, Thomas G.},
  title           = {Ensemble Methods in Machine Learning},
  year            = 2000,
  booktitle       = {Proceedings of the First International Workshop on Multiple Classifier Systems},
  series          = {MCS '00},
  publisher       = {Springer-Verlag},
  isbn            = {3-540-67704-6},
  pages           = {1--15},
  url             = {http://dl.acm.org/citation.cfm?id=648054.743935},
  acmid           = 743935,
  address         = {London, UK, UK},
  numpages        = 15,
  timestamp       = {20181201T1029}
}

@Article{ding2013-evolutionary,
  author          = {Ding, Shifei and Li, Hui and Su, Chunyang and Yu, Junzhao and Jin, Fengxiang},
  title           = {Evolutionary Artificial Neural Networks: a Review},
  journaltitle    = {Artif. Intell. Rev.},
  year            = 2013,
  volume          = 39,
  number          = 3,
  month           = mar,
  pages           = {251--260},
  issn            = {0269-2821},
  doi             = {10.1007/s10462-011-9270-6},
  url             = {https://doi.org/10.1007/s10462-011-9270-6},
  journal         = {Artif. Intell. Rev.},
  acmid           = 2447414,
  address         = {Norwell, MA, USA},
  issue_date      = {March 2013},
  keywords        = {Artificial Neural Networks (ANNs), Evolution Algorithms (EAs), Network architecture, Weights},
  numpages        = 10,
  publisher       = {Kluwer Academic Publishers},
  timestamp       = {20181201T1029}
}

@Article{ding2014-mental,
  author          = {Ding, Weiguang and Taylor, Graham W},
  title           = {Mental Rotation By Optimizing Transforming Distance},
  journaltitle    = {arXiv preprint arXiv:1406.3010},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1406.3010},
  timestamp       = {20190110T0939}
}

@Article{dinh2017-sharp,
  author          = {{Dinh}, L. and {Pascanu}, R. and {Bengio}, S. and {Bengio}, Y.},
  title           = {{Sharp Minima Can Generalize for Deep Nets}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.04933},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1029}
}

@Article{dipietro2017-revisiting,
  author          = {Robert DiPietro and Nassir Navab and Gregory D. Hager},
  title           = {Revisiting {NARX} Recurrent Neural Networks for Long-Term Dependencies},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1702.07805},
  url             = {http://arxiv.org/abs/1702.07805},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DiPietroNH17},
  timestamp       = {20181201T1029}
}

@Article{doersch2015-unsupervised,
  author          = {Carl Doersch and Abhinav Gupta and Alexei A. Efros},
  title           = {Unsupervised Visual Representation Learning By Context Prediction},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1505.05192},
  url             = {http://arxiv.org/abs/1505.05192},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DoerschGE15},
  timestamp       = {20181201T1029}
}

@Article{dominey2000-neural,
  author          = {Dominey, Peter Ford and Ramus, Franck},
  title           = {Neural Network Processing of Natural Language: I. Sensitivity To Serial, Temporal and Abstract Structure of Language in
                  the Infant},
  journaltitle    = {Language and Cognitive Processes},
  year            = 2000,
  volume          = 15,
  number          = 1,
  pages           = {87--127},
  journal         = {Language and Cognitive Processes},
  publisher       = {Taylor \& Francis},
  timestamp       = {20181201T1029}
}

@Article{domingos2012-few,
  author          = {Domingos, Pedro},
  title           = {A Few Useful Things To Know About Machine Learning},
  journaltitle    = {Commun. ACM},
  year            = 2012,
  volume          = 55,
  number          = 10,
  month           = oct,
  pages           = {78--87},
  issn            = {0001-0782},
  doi             = {10.1145/2347736.2347755},
  url             = {https://doi.org/10.1145/2347736.2347755},
  journal         = {Commun. ACM},
  acmid           = 2347755,
  address         = {New York, NY, USA},
  issue_date      = {October 2012},
  numpages        = 10,
  publisher       = {ACM},
  timestamp       = {20181201T1029}
}

@Article{donahue2016-adversarial,
  author          = {Jeff Donahue and Philipp Kr{\"{a}}henb{\"{u}}hl and Trevor Darrell},
  title           = {Adversarial Feature Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1605.09782},
  url             = {http://arxiv.org/abs/1605.09782},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DonahueKD16},
  timestamp       = {20181201T1029}
}

@Article{dong2017-boosting,
  author          = {Yinpeng Dong and Fangzhou Liao and Tianyu Pang and Xiaolin Hu and Jun Zhu},
  title           = {Boosting Adversarial Attacks With Momentum},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1710.06081},
  journal         = {CoRR},
  keywords        = {adversarial, mifgm},
  timestamp       = {20181201T1029}
}

@InCollection{dong2017-learning,
  author          = {Dong, Xin and Chen, Shangyu and Pan, Sinno},
  title           = {Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4860--4874},
  url             = {http://papers.nips.cc/paper/7071-learning-to-prune-deep-neural-networks-via-layer-wise-optimal-brain-surgeon.pdf},
  timestamp       = {20181201T1029}
}

@Article{dong2017-towards,
  author          = {Dong, Yinpeng and Su, Hang and Zhu, Jun and Bao, Fan},
  title           = {Towards Interpretable Deep Neural Networks By Leveraging Adversarial Examples},
  journaltitle    = {arXiv preprint arXiv:1708.05493},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1708.05493},
  keywords        = {adversarial, representation, interpretability},
  timestamp       = {20181201T1029}
}

@Article{dong2018-training,
  author          = {Dong, Hao-Wen and Yang, Yi-Hsuan},
  title           = {Training Generative Adversarial Networks With Binary Neurons By End-To-End Backpropagation},
  journaltitle    = {arXiv preprint arXiv:1810.04714},
  year            = 2018,
  journal         = {arXiv preprint arXiv:1810.04714},
  keywords        = {quantization, binarygan},
  timestamp       = {20181201T1029}
}

@InProceedings{dosovitskiy2014-discriminative,
  author          = {Dosovitskiy, Alexey and Springenberg, Jost Tobias and Riedmiller, Martin and Brox, Thomas},
  title           = {Discriminative unsupervised feature learning with convolutional neural networks},
  year            = 2014,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {766--774},
  timestamp       = {20181201T1029}
}

@Article{dosovitskiy2015-inverting,
  author          = {Alexey Dosovitskiy and Thomas Brox},
  title           = {Inverting Convolutional Networks With Convolutional Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.02753},
  url             = {http://arxiv.org/abs/1506.02753},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/DosovitskiyB15},
  timestamp       = {20181201T1029}
}

@InCollection{downey2017-predictive,
  author          = {Downey, Carlton and Hefny, Ahmed and Boots, Byron and Gordon, Geoffrey J and Li, Boyue},
  title           = {Predictive State Recurrent Neural Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6055--6066},
  url             = {http://papers.nips.cc/paper/7186-predictive-state-recurrent-neural-networks.pdf},
  timestamp       = {20181201T1029}
}

@Article{draelos2016-neurogenesis,
  author          = {{Draelos}, T.~J. and {Miner}, N.~E. and {Lamb}, C.~C. and {Vineyard}, C.~M. and {Carlson}, K.~D. and {James}, C.~D. and
                  {Aimone}, J.~B.},
  title           = {{Neurogenesis Deep Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = dec,
  eprint          = {1612.03770},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Neural and Evolutionary Computing, Computer Science - Learning, Statistics - Machine Learning},
  timestamp       = {20181201T1029}
}

@Article{drucker1992-improving,
  author          = {Drucker, H. and Le Cun, Y.},
  title           = {Improving Generalization Performance Using Double Backpropagation},
  journaltitle    = {Trans. Neur. Netw.},
  year            = 1992,
  volume          = 3,
  number          = 6,
  month           = nov,
  pages           = {991--997},
  issn            = {1045-9227},
  doi             = {10.1109/72.165600},
  url             = {https://doi.org/10.1109/72.165600},
  journal         = {Trans. Neur. Netw.},
  acmid           = 2327904,
  address         = {Piscataway, NJ, USA},
  issue_date      = {November 1992},
  numpages        = 7,
  publisher       = {IEEE Press},
  timestamp       = {20181201T1029}
}

@Article{drusvyatskiy2016-optimal,
  author          = {Drusvyatskiy, Dmitriy and Fazel, Maryam and Roy, Scott},
  title           = {An Optimal First Order Method Based on Optimal Quadratic Averaging},
  journaltitle    = {arXiv preprint arXiv:1604.06543},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1604.06543},
  timestamp       = {20181201T1029}
}

@Article{du2018-gradient,
  author          = {{Du}, S.~S. and {Zhai}, X. and {Poczos}, B. and {Singh}, A.},
  title           = {{Gradient Descent Provably Optimizes Over-Parameterized Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = oct,
  eprint          = {1810.02054},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv181002054D},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Machine Learning, Mathematics - Optimization and Control, Statistics - Machine Learning},
  timestamp       = {20181201T1029}
}

@InProceedings{du2018-when,
  author          = {Simon S. Du and Jason D. Lee and Yuandong Tian},
  title           = {When is a Convolutional Filter Easy to Learn?},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SkA-IE06W},
  timestamp       = {20181201T1029}
}

@Article{duan2016-benchmarking,
  author          = {Yan Duan and Xi Chen and Rein Houthooft and John Schulman and Pieter Abbeel},
  title           = {Benchmarking Deep Reinforcement Learning for Continuous Control},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.06778},
  eprint          = {1604.06778},
  url             = {http://arxiv.org/abs/1604.06778},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/DuanCHSA16},
  timestamp       = {Mon, 03 Sep 2018 12:15:29 +0200}
}

@Article{duan2016-rl,
  author          = {Duan, Yan and Schulman, John and Chen, Xi and Bartlett, Peter L and Sutskever, Ilya and Abbeel, Pieter},
  title           = {Rl $\^{} 2$: Fast Reinforcement Learning Via Slow Reinforcement Learning},
  journaltitle    = {arXiv preprint arXiv:1611.02779},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1611.02779},
  timestamp       = {20181201T1029}
}

@InCollection{duan2017-one,
  author          = {Duan, Yan and Andrychowicz, Marcin and Stadie, Bradly and Jonathan Ho, OpenAI and Schneider, Jonas and Sutskever, Ilya
                  and Abbeel, Pieter and Zaremba, Wojciech},
  title           = {One-Shot Imitation Learning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1087--1098},
  url             = {http://papers.nips.cc/paper/6709-one-shot-imitation-learning.pdf},
  timestamp       = {20181201T1029}
}

@Article{dubey2018-investigating,
  author          = {{Dubey}, R. and {Agrawal}, P. and {Pathak}, D. and {Griffiths}, T.~L. and {Efros}, A.~A.},
  title           = {{Investigating Human Priors for Playing Video Games}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.10217},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180210217D},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1029}
}

@Misc{duffy2017-year,
  author          = {Benjamin F. Duffy and Daniel R. Flynn},
  title           = {A Year in Computer Vision},
  year            = 2017,
  timestamp       = {20181201T1029}
}

@Article{dumont2018-robustness,
  author          = {Beranger Dumont and Simona Maggio and Pablo Montalvo},
  title           = {Robustness of Rotation-Equivariant Networks To Adversarial Perturbations},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1802.06627},
  eprint          = {1802.06627},
  url             = {http://arxiv.org/abs/1802.06627},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1802-06627},
  keywords        = {adversarial, defense},
  timestamp       = {20181201T1029}
}

@Article{dumoulin2016-adversarially,
  author          = {{Dumoulin}, V. and {Belghazi}, I. and {Poole}, B. and {Mastropietro}, O. and {Lamb}, A. and {Arjovsky}, M. and
                  {Courville}, A.},
  title           = {{Adversarially Learned Inference}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.00704},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1029}
}

@Article{dupoux2016-cognitive,
  author          = {Emmanuel Dupoux},
  title           = {Cognitive Science in the Era of Artificial Intelligence: {A} Roadmap for Reverse-Engineering the Infant
                  Language-Learner},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1607.08723},
  eprint          = {1607.08723},
  url             = {http://arxiv.org/abs/1607.08723},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/Dupoux16},
  timestamp       = {20181201T1029}
}

@InProceedings{duvenaud2014-avoiding,
  author          = {Duvenaud, David K and Rippel, Oren and Adams, Ryan P and Ghahramani, Zoubin},
  title           = {Avoiding pathologies in very deep networks.},
  year            = 2014,
  booktitle       = {AISTATS},
  pages           = {202--210},
  timestamp       = {20181201T1029}
}

@InCollection{duvenaud2015-convolutional,
  author          = {Duvenaud, David K and Maclaurin, Dougal and Iparraguirre, Jorge and Bombarell, Rafael and Hirzel, Timothy and
                  Aspuru-Guzik, Alan and Adams, Ryan P},
  title           = {Convolutional Networks on Graphs for Learning Molecular Fingerprints},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2224--2232},
  url             = {http://papers.nips.cc/paper/5954-convolutional-networks-on-graphs-for-learning-molecular-fingerprints.pdf},
  timestamp       = {20181201T1029}
}

@Article{dziugaite2017-computing,
  author          = {Dziugaite, Gintare Karolina and Roy, Daniel M},
  title           = {Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks With Many More Parameters Than
                  Training Data},
  journaltitle    = {arXiv preprint arXiv:1703.11008},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1703.11008},
  timestamp       = {20181201T1029}
}

@Book{easley2010-networks,
  author          = {Easley, David and Kleinberg, Jon},
  title           = {Networks, crowds, and markets: Reasoning about a highly connected world},
  year            = 2010,
  publisher       = {Cambridge University Press},
  timestamp       = {20181201T1030}
}

@InProceedings{eastwood2018-framework,
  author          = {Cian Eastwood and Christopher K. I. Williams},
  title           = {A Framework for the Quantitative Evaluation of Disentangled Representations},
  keywords        = {disentangle},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=By-7dz-AZ},
  timestamp       = {20181201T1030}
}

@Article{ebrahimi2017-hotflip,
  author          = {{Ebrahimi}, J. and {Rao}, A. and {Lowd}, D. and {Dou}, D.},
  title           = {{HotFlip: White-Box Adversarial Examples for NLP}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.06751},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171206751E},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack, text, hotflip, one-hot},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{efros2001-image,
  author          = {Efros, Alexei A. and Freeman, William T.},
  title           = {Image Quilting for Texture Synthesis and Transfer},
  year            = 2001,
  booktitle       = {Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques},
  series          = {SIGGRAPH '01},
  publisher       = {ACM},
  isbn            = {1-58113-374-X},
  pages           = {341--346},
  doi             = {10.1145/383259.383296},
  url             = {https://doi.org/10.1145/383259.383296},
  acmid           = 383296,
  address         = {New York, NY, USA},
  keywords        = {image-based rendering, texture mapping, texture synthesis},
  numpages        = 6,
  timestamp       = {20181201T1030}
}

@Article{eickenberg2016-seeing,
  author          = "Michael Eickenberg and Alexandre Gramfort and Ga{\"e}l Varoquaux and Bertrand Thirion",
  title           = {Seeing It All: Convolutional Network Layers Map the Function of the Human Visual System},
  journaltitle    = "NeuroImage",
  year            = 2016,
  issn            = "1053-8119",
  doi             = {10.1016/j.neuroimage.2016.10.001},
  url             = {https://doi.org/10.1016/j.neuroimage.2016.10.001},
  journal         = "NeuroImage",
  timestamp       = {20181201T1030}
}

@Article{elgammal2017-can,
  author          = {Ahmed M. Elgammal and Bingchen Liu and Mohamed Elhoseiny and Marian Mazzone},
  title           = {{CAN:} Creative Adversarial Networks, Generating "Art" By Learning About Styles and Deviating From Style Norms},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.07068},
  url             = {http://arxiv.org/abs/1706.07068},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{elhamifar2012-sparse,
  author          = {Ehsan Elhamifar and Ren{\'{e}} Vidal},
  title           = {Sparse Subspace Clustering: Algorithm, Theory, and Applications},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1203.1005},
  journal         = {CoRR},
  keywords        = {cluster},
  timestamp       = {20181201T1030}
}

@InCollection{elhamifar2017-subset,
  author          = {Elhamifar, Ehsan and De Paolis Kaluza, M. Clara},
  title           = {Subset Selection and Summarization in Sequential Data},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1036--1045},
  url             = {http://papers.nips.cc/paper/6704-subset-selection-and-summarization-in-sequential-data.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{emamjomeh-zadeh2017-general,
  author          = {Emamjomeh-Zadeh, Ehsan and Kempe, David},
  title           = {A General Framework for Robust Interactive Learning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {7085--7094},
  url             = {http://papers.nips.cc/paper/7283-a-general-framework-for-robust-interactive-learning.pdf},
  timestamp       = {20181201T1030}
}

@Book{engel2001-statistical,
  author          = {Engel, Andreas and Van den Broeck, Christian},
  title           = {Statistical mechanics of learning},
  year            = 2001,
  publisher       = {Cambridge University Press},
  timestamp       = {20181201T1030}
}

@Article{engels2007-plagiarism,
  author          = {Engels, Steve and Lakshmanan, Vivek and Craig, Michelle},
  title           = {Plagiarism Detection Using Feature-Based Neural Networks},
  journaltitle    = {SIGCSE Bull.},
  year            = 2007,
  volume          = 39,
  number          = 1,
  month           = mar,
  pages           = {34--38},
  issn            = {0097-8418},
  doi             = {10.1145/1227504.1227324},
  url             = {https://doi.org/10.1145/1227504.1227324},
  journal         = {SIGCSE Bull.},
  acmid           = 1227324,
  address         = {New York, NY, USA},
  issue_date      = {March 2007},
  keywords        = {cheating, features, introductory computer science, neural networks, plagiarism detection},
  numpages        = 5,
  publisher       = {ACM},
  timestamp       = {20181201T1030}
}

@Article{erhan2009-visualizing,
  author          = {Erhan, Dumitru and Bengio, Yoshua and Courville, Aaron and Vincent, Pascal},
  title           = {Visualizing Higher-Layer Features of a Deep Network},
  journaltitle    = {University of Montreal},
  year            = 2009,
  volume          = 1341,
  number          = 3,
  pages           = 1,
  journal         = {University of Montreal},
  keywords        = {interpret, activation maximization},
  timestamp       = {20181201T1030}
}

@Article{erhan2010-why,
  author          = {Erhan, Dumitru and Bengio, Yoshua and Courville, Aaron and Manzagol, Pierre-Antoine and Vincent, Pascal and Bengio,
                  Samy},
  title           = {Why Does Unsupervised Pre-Training Help Deep Learning?},
  journaltitle    = {J. Mach. Learn. Res.},
  year            = 2010,
  volume          = 11,
  month           = mar,
  pages           = {625--660},
  issn            = {1532-4435},
  url             = {http://dl.acm.org/citation.cfm?id=1756006.1756025},
  journal         = {J. Mach. Learn. Res.},
  acmid           = 1756025,
  issue_date      = {3/1/2010},
  numpages        = 36,
  publisher       = {JMLR.org},
  timestamp       = {20181201T1030}
}

@Article{erraqabi2018-a3t,
  author          = {{Erraqabi}, A. and {Baratin}, A. and {Bengio}, Y. and {Lacoste-Julien}, S.},
  title           = {{A3T: Adversarially Augmented Adversarial Training}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.04055},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180104055E},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{esfandarani2017-nima,
  author          = {Hossein Talebi Esfandarani and Peyman Milanfar},
  title           = {{NIMA:} Neural Image Assessment},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1709.05424},
  journal         = {CoRR},
  keywords        = {quality, emd},
  timestamp       = {20181201T1030}
}

@Article{espeholt2018-impala,
  author          = {{Espeholt}, L. and {Soyer}, H. and {Munos}, R. and {Simonyan}, K. and {Mnih}, V. and {Ward}, T. and {Doron}, Y. and
                  {Firoiu}, V. and {Harley}, T. and {Dunning}, I. and {Legg}, S. and {Kavukcuoglu}, K.},
  title           = {{IMPALA: Scalable Distributed Deep-Rl With Importance Weighted Actor-Learner Architectures}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.01561},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180201561E},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InProceedings{esser2015-backpropagation,
  author          = {Esser, Steve K and Appuswamy, Rathinakumar and Merolla, Paul and Arthur, John V and Modha, Dharmendra S},
  title           = {Backpropagation for energy-efficient neuromorphic computing},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {1117--1125},
  keywords        = {quantization, spiking},
  timestamp       = {20181201T1030}
}

@Article{esteva2017-dermatologist,
  author          = {Esteva, Andre and Kuprel, Brett and Novoa, Roberto A.  and Ko, Justin and Swetter, Susan M.  and Blau, Helen M.  and
                  Thrun, Sebastian},
  title           = {Dermatologist-Level Classification of Skin Cancer With Deep Neural Networks},
  journaltitle    = {Nature},
  year            = 2017,
  volume          = {advance online publication},
  month           = {Jan},
  note            = {Letter},
  issn            = {1476-4687},
  url             = {http://dx.doi.org/10.1038/nature21056},
  journal         = {Nature},
  day             = 25,
  publisher       = {Macmillan Publishers Limited, part of Springer Nature. All rights reserved.},
  timestamp       = {20181201T1030}
}

@Article{evans2017-learning,
  author          = {Richard Evans and Edward Grefenstette},
  title           = {Learning Explanatory Rules From Noisy Data},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.04574},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{everingham2010-pascal,
  author          = {Everingham, Mark and Van Gool, Luc and Williams, Christopher KI and Winn, John and Zisserman, Andrew},
  title           = {The Pascal Visual Object Classes (VOC) Challenge},
  journaltitle    = {International journal of computer vision},
  year            = 2010,
  volume          = 88,
  number          = 2,
  pages           = {303--338},
  journal         = {International journal of computer vision},
  keywords        = {data, voc},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{evtimov2017-robust,
  author          = {{Evtimov}, I. and {Eykholt}, K. and {Fernandes}, E. and {Kohno}, T. and {Li}, B. and {Prakash}, A. and {Rahmati},
                  A. and {Song}, D.},
  title           = {{Robust Physical-World Attacks on Machine Learning Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.08945},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Cryptography and Security, Computer Science - Learning},
  primaryclass    = "cs.CR",
  timestamp       = {20181201T1030}
}

@Article{fabius2014-variational,
  author          = {{Fabius}, O. and {van Amersfoort}, J.~R.},
  title           = {{Variational Recurrent Auto-Encoders}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = dec,
  eprint          = {1412.6581},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InCollection{fahlman1990-cascade,
  author          = {Fahlman, Scott E. and Lebiere, Christian},
  title           = {The Cascade-correlation Learning Architecture},
  year            = 1990,
  booktitle       = {NIPS},
  editor          = {Touretzky, David S.},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  isbn            = {1-55860-100-7},
  chapter         = {Advances in Neural Information Processing Systems 2},
  pages           = {524--532},
  url             = {http://dl.acm.org/citation.cfm?id=109230.107380},
  acmid           = 107380,
  address         = {San Francisco, CA, USA},
  numpages        = 9,
  timestamp       = {20181201T1030}
}

@InCollection{fan2015-fast,
  author          = {Fan, Kai and Wang, Ziteng and Beck, Jeff and Kwok, James and Heller, Katherine A},
  title           = {Fast Second Order Stochastic Backpropagation for Variational Inference},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1387--1395},
  url             = {http://papers.nips.cc/paper/5670-fast-second-order-stochastic-backpropagation-for-variational-inference.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{fan2017-revisit,
  author          = {Fan, Lixin},
  title           = {Revisit Fuzzy Neural Network: Demystifying Batch Normalization and ReLU with Generalized Hamming Network},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1920--1929},
  url             = {http://papers.nips.cc/paper/6788-revisit-fuzzy-neural-network-demystifying-batch-normalization-and-relu-with-generalized-hamming-network.pdf},
  timestamp       = {20181201T1030}
}

@Article{fan2018-learning,
  author          = {Yang Fan and Fei Tian and Tao Qin and Xiang{-}Yang Li and Tie{-}Yan Liu},
  title           = {Learning To Teach},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1805.03643},
  eprint          = {1805.03643},
  url             = {http://arxiv.org/abs/1805.03643},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1805-03643},
  timestamp       = {20190107T1425}
}

@InProceedings{farabet2010-hardware,
  author          = {Farabet, Cl{\'e}ment and Martini, Berin and Akselrod, Polina and Talay, Sel{\c{c}}uk and LeCun, Yann and Culurciello,
                  Eugenio},
  title           = {Hardware accelerated convolutional neural networks for synthetic vision systems},
  year            = 2010,
  booktitle       = {Proceedings of 2010 IEEE International Symposium on Circuits and Systems},
  organization    = {IEEE},
  pages           = {257--260},
  timestamp       = {20181201T1030}
}

@Article{fawzi2015-analysis,
  author          = {Alhussein Fawzi and Omar Fawzi and Pascal Frossard},
  title           = {Analysis of Classifiers' Robustness To Adversarial Perturbations},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1502.02590},
  url             = {http://arxiv.org/abs/1502.02590},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/FawziFF15},
  keywords        = {theory, adversarial, distinguishability},
  timestamp       = {20181201T1030}
}

@Article{fawzi2015-dictionary,
  author          = {Fawzi, Alhussein and Davies, Mike and Frossard, Pascal},
  title           = {Dictionary Learning for Fast Classification Based on Soft-Thresholding},
  journaltitle    = {International Journal of Computer Vision},
  year            = 2015,
  volume          = 114,
  number          = {2-3},
  pages           = {306--321},
  journal         = {International Journal of Computer Vision},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@InProceedings{fawzi2015-fundamental,
  author          = {Fawzi, Alhussein and Fawzi, Omar and Frossard, Pascal},
  title           = {Fundamental limits on adversarial robustness},
  year            = 2015,
  booktitle       = {Proc. ICML, Workshop on Deep Learning},
  timestamp       = {20181201T1030}
}

@InProceedings{fawzi2016-robustness,
  author          = {Fawzi, Alhussein and Moosavi-Dezfooli, Seyed-Mohsen and Frossard, Pascal},
  title           = {Robustness of classifiers: from adversarial to random noise},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {1624--1632},
  keywords        = {adversarial, hypothesis, curvature, decision boundary},
  timestamp       = {20181201T1030}
}

@InProceedings{fedus2018-maskgan,
  author          = {William Fedus and Ian Goodfellow and Andrew M. Dai},
  title           = {Mask{GAN}: Better Text Generation via Filling in the _______},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=ByOExmWAb},
  timestamp       = {20181201T1030}
}

@Article{fei-fei2006-one,
  author          = {Fei-Fei, Li and Fergus, Rob and Perona, Pietro},
  title           = {One-Shot Learning of Object Categories},
  journaltitle    = {IEEE transactions on pattern analysis and machine intelligence},
  year            = 2006,
  volume          = 28,
  number          = 4,
  pages           = {594--611},
  journal         = {IEEE transactions on pattern analysis and machine intelligence},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@InProceedings{feng2015-learning,
  author          = {Feng, Jiashi and Darrell, Trevor},
  title           = {Learning the structure of deep convolutional networks},
  year            = 2015,
  booktitle       = {Proceedings of the IEEE International Conference on Computer Vision},
  pages           = {2749--2757},
  timestamp       = {20181201T1030}
}

@Article{feng2017-autoencoder,
  author          = {Ji Feng and Zhi{-}Hua Zhou},
  title           = {Autoencoder By Forest},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1709.09018},
  eprint          = {1709.09018},
  url             = {http://arxiv.org/abs/1709.09018},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1709-09018},
  timestamp       = {20181201T1030}
}

@InProceedings{fernando2003-pattern,
  author          = {Fernando, Chrisantha and Sojakka, Sampsa},
  title           = {Pattern recognition in a bucket},
  year            = 2003,
  booktitle       = {European Conference on Artificial Life},
  organization    = {Springer},
  pages           = {588--597},
  keywords        = {reservoir},
  timestamp       = {20181201T1030}
}

@Article{fernando2016-convolution,
  author          = {Chrisantha Fernando and Dylan Banarse and Malcolm Reynolds and Frederic Besse and David Pfau and Max Jaderberg and Marc
                  Lanctot and Daan Wierstra},
  title           = {Convolution By Evolution: Differentiable Pattern Producing Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.02580},
  url             = {http://arxiv.org/abs/1606.02580},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/FernandoBRBPJLW16},
  timestamp       = {20181201T1030}
}

@InCollection{feurer2015-efficient,
  author          = {Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina and Springenberg, Jost and Blum, Manuel and Hutter,
                  Frank},
  title           = {Efficient and Robust Automated Machine Learning},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2962--2970},
  url             = {http://papers.nips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf},
  timestamp       = {20181201T1030}
}

@Article{feutry2018-learning,
  author          = {{Feutry}, C. and {Piantanida}, P. and {Bengio}, Y. and {Duhamel}, P.},
  title           = {{Learning Anonymized Representations With Adversarial Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.09386},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180209386F},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Cryptography and Security, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{fidler2012-object,
  author          = {Fidler, Sanja and Dickinson, Sven and Urtasun, Raquel},
  title           = {3D Object Detection and Viewpoint Estimation with A Deformable 3D Cuboid Model},
  year            = 2012,
  booktitle       = {Advances in neural information processing systems},
  pages           = {611--619},
  timestamp       = {20190110T1004}
}

@InProceedings{fiesler1990-weight,
  author          = {Fiesler, Emile and Choudry, Amar and Caulfield, H John},
  title           = {Weight discretization paradigm for optical neural networks},
  year            = 1990,
  booktitle       = {The Hague'90, 12-16 April},
  organization    = {International Society for Optics and Photonics},
  pages           = {164--173},
  timestamp       = {20181201T1030}
}

@Article{figurnov2016-spatially,
  author          = {{Figurnov}, M. and {Collins}, M.~D. and {Zhu}, Y. and {Zhang}, L. and {Huang}, J. and {Vetrov}, D. and {Salakhutdinov},
                  R.},
  title           = {{Spatially Adaptive Computation Time for Residual Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = dec,
  eprint          = {1612.02297},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@InProceedings{finkelstein2001-placing,
  author          = {Finkelstein, Lev and Gabrilovich, Evgeniy and Matias, Yossi and Rivlin, Ehud and Solan, Zach and Wolfman, Gadi and
                  Ruppin, Eytan},
  title           = {Placing search in context: The concept revisited},
  year            = 2001,
  booktitle       = {Proceedings of the 10th international conference on World Wide Web},
  organization    = {ACM},
  pages           = {406--414},
  keywords        = {wordsim},
  timestamp       = {20181201T1030}
}

@Article{finn2017-model,
  author          = {Chelsea Finn and Pieter Abbeel and Sergey Levine},
  title           = {Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.03400},
  journal         = {CoRR},
  keywords        = {meta learning, maml},
  timestamp       = {20181201T1030}
}

@Article{fischer2014-training,
  author          = {Fischer, Asja and Igel, Christian},
  title           = {Training Restricted Boltzmann Machines: an Introduction},
  journaltitle    = {Pattern Recogn.},
  year            = 2014,
  volume          = 47,
  number          = 1,
  month           = jan,
  pages           = {25--39},
  issn            = {0031-3203},
  doi             = {10.1016/j.patcog.2013.05.025},
  url             = {https://doi.org/10.1016/j.patcog.2013.05.025},
  journal         = {Pattern Recogn.},
  acmid           = 2533561,
  address         = {New York, NY, USA},
  issue_date      = {January, 2014},
  keywords        = {Contrastive divergence learning, Gibbs sampling, Markov chains, Markov random fields, Neural networks, Parallel
                  tempering, Restricted Boltzmann machines},
  numpages        = 15,
  publisher       = {Elsevier Science Inc.},
  timestamp       = {20181201T1030}
}

@Article{fischer2015-flownet,
  author          = {Philipp Fischer and Alexey Dosovitskiy and Eddy Ilg and Philip H{\"{a}}usser and Caner Hazirbas and Vladimir Golkov and
                  Patrick van der Smagt and Daniel Cremers and Thomas Brox},
  title           = {Flownet: Learning Optical Flow With Convolutional Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1504.06852},
  url             = {http://arxiv.org/abs/1504.06852},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/FischerDIHHGSCB15},
  timestamp       = {20181201T1029}
}

@InCollection{fleet2006-optical,
  author          = {Fleet, David and Weiss, Yair},
  title           = {Optical flow estimation},
  year            = 2006,
  booktitle       = {Handbook of mathematical models in computer vision},
  publisher       = {Springer},
  pages           = {237--257},
  timestamp       = {20181201T1030}
}

@Article{floreano2008-neuroevolution,
  author          = {Floreano, Dario and D{\"u}rr, Peter and Mattiussi, Claudio},
  title           = {Neuroevolution: From Architectures To Learning},
  journaltitle    = {Evolutionary Intelligence},
  year            = 2008,
  volume          = 1,
  number          = 1,
  pages           = {47--62},
  journal         = {Evolutionary Intelligence},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{foerster2017-learning,
  author          = {{Foerster}, J.~N. and {Chen}, R.~Y. and {Al-Shedivat}, M. and {Whiteson}, S. and {Abbeel}, P. and {Mordatch}, I.},
  title           = {{Learning With Opponent-Learning Awareness}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = sep,
  eprint          = {1709.04326},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Computer Science and Game Theory},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@Article{fogel1994-introduction,
  author          = {D. B. Fogel},
  title           = {An Introduction To Simulated Evolutionary Optimization},
  journaltitle    = {IEEE Transactions on Neural Networks},
  year            = 1994,
  volume          = 5,
  number          = 1,
  month           = Jan,
  pages           = {3-14},
  issn            = {1045-9227},
  doi             = {10.1109/72.265956},
  url             = {https://doi.org/10.1109/72.265956},
  journal         = {IEEE Transactions on Neural Networks},
  keywords        = {genetic algorithms;optimisation;behavioral change;chromosomal operators;evolution strategies;evolutionary
                  programming;genetic algorithms;population-based optimization;simulated evolutionary optimization;Biological
                  cells;Computational modeling;Computer simulation;Cost function;Evolution (biology);Genetic algorithms;Genetic
                  mutations;Genetic programming;Optimization methods;Stress},
  timestamp       = {20181201T1030}
}

@Article{fortunato2017-noisy,
  author          = {{Fortunato}, M. and {Gheshlaghi Azar}, M. and {Piot}, B. and {Menick}, J. and {Osband}, I. and {Graves}, A. and {Mnih},
                  V. and {Munos}, R. and {Hassabis}, D. and {Pietquin}, O. and {Blundell}, C. and {Legg}, S.},
  title           = {{Noisy Networks for Exploration}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.10295},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InProceedings{fraccaro2016-sequential,
  author          = {Fraccaro, Marco and S{\o}nderby, S{\o}ren Kaae and Paquet, Ulrich and Winther, Ole},
  title           = {Sequential neural models with stochastic layers},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {2199--2207},
  timestamp       = {20181201T1030}
}

@Article{franz1995-recipes,
  author          = {Franz, Silvio and Parisi, Giorgio},
  title           = {Recipes for Metastable States in Spin Glasses},
  journaltitle    = {Journal de Physique I},
  year            = 1995,
  volume          = 5,
  number          = 11,
  pages           = {1401--1415},
  journal         = {Journal de Physique I},
  publisher       = {EDP Sciences},
  timestamp       = {20181201T1030}
}

@Article{freeman2016-topology,
  author          = {{Freeman}, C.~D. and {Bruna}, J.},
  title           = {{Topology and Geometry of Half-Rectified Network Optimization}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = nov,
  eprint          = {1611.01540},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2016arXiv161101540F},
  archiveprefix   = "arXiv",
  keywords        = {theory, loss surface, level set},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{french1999-catastrophic,
  author          = {French, Robert M},
  title           = {Catastrophic Forgetting in Connectionist Networks},
  journaltitle    = {Trends in cognitive sciences},
  year            = 1999,
  volume          = 3,
  number          = 4,
  pages           = {128--135},
  journal         = {Trends in cognitive sciences},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{freund2003-efficient,
  author          = {Freund, Yoav and Iyer, Raj and Schapire, Robert E and Singer, Yoram},
  title           = {An Efficient Boosting Algorithm for Combining Preferences},
  journaltitle    = {Journal of machine learning research},
  year            = 2003,
  volume          = 4,
  number          = {Nov},
  pages           = {933--969},
  journal         = {Journal of machine learning research},
  keywords        = {learning to rank},
  timestamp       = {20181201T1030}
}

@Article{friedman2001-greedy,
  author          = {Friedman, Jerome H},
  title           = {Greedy Function Approximation: a Gradient Boosting Machine},
  journaltitle    = {Annals of statistics},
  year            = 2001,
  pages           = {1189--1232},
  journal         = {Annals of statistics},
  publisher       = {JSTOR},
  timestamp       = {20181201T1030}
}

@Article{fulcher2014-highly,
  author          = {Ben D. Fulcher and Nick S. Jones},
  title           = {Highly Comparative, Feature-Based Time-Series Classification},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1401.3531},
  url             = {http://arxiv.org/abs/1401.3531},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/FulcherJ14},
  timestamp       = {20181201T1030}
}

@InCollection{gabrie2015-training,
  author          = {Gabrie, Marylou and Tramel, Eric W and Krzakala, Florent},
  title           = {Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {640--648},
  url             = {http://papers.nips.cc/paper/5788-training-restricted-boltzmann-machine-via-the-thouless-anderson-palmer-free-energy.pdf},
  timestamp       = {20181201T1030}
}

@Article{gal2015-theoretically,
  author          = {{Gal}, Y.},
  title           = {{A Theoretically Grounded Application of Dropout in Recurrent Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = dec,
  eprint          = {1512.05287},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{gal2016-dropout,
  author          = {Gal, Yarin and Ghahramani, Zoubin},
  title           = {Dropout as a Bayesian approximation: Representing model uncertainty in deep learning},
  year            = 2016,
  booktitle       = {international conference on machine learning},
  pages           = {1050--1059},
  keywords        = {bayesian, dropout, bn},
  timestamp       = {20181201T1030}
}

@Thesis{gal2016-uncertainty,
  author          = {Gal, Yarin},
  title           = {Uncertainty In Deep Learning},
  type            = {Phd},
  institution     = {University of Cambridge},
  year            = 2016,
  timestamp       = {20181201T1030}
}

@InCollection{gal2017-concrete,
  author          = {Gal, Yarin and Hron, Jiri and Kendall, Alex},
  title           = {Concrete Dropout},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3584--3593},
  url             = {http://papers.nips.cc/paper/6949-concrete-dropout.pdf},
  timestamp       = {20181201T1030}
}

@Thesis{gallagher2000-multi,
  author          = {Gallagher, Marcus},
  title           = {Multi-layer perceptron error surfaces: visualization, structure and modelling},
  type            = {PhD},
  institution     = {University of Queensland},
  year            = 2000,
  keywords        = {loss surface},
  school          = {University of Queensland},
  timestamp       = {20181201T1030}
}

@InProceedings{galloway2018-attacking,
  author          = {Angus Galloway and Graham W. Taylor and Medhat Moussa},
  title           = {Attacking Binarized Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HkTEFfZRb},
  keywords        = {adversarial, attack, bnn},
  timestamp       = {20181201T1030}
}

@Article{galloway2018-predicting,
  author          = {{Galloway}, A. and {Taylor}, G.~W. and {Moussa}, M.},
  title           = {{Predicting Adversarial Examples With High Confidence}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.04457},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180204457G},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InCollection{gan2015-deep,
  author          = {Gan, Zhe and Li, Chunyuan and Henao, Ricardo and Carlson, David E and Carin, Lawrence},
  title           = {Deep Temporal Sigmoid Belief Networks for Sequence Modeling},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2467--2475},
  url             = {http://papers.nips.cc/paper/5655-deep-temporal-sigmoid-belief-networks-for-sequence-modeling.pdf},
  timestamp       = {20181201T1030}
}

@Article{ganin2015-domain,
  author          = {{Ganin}, Y. and {Ustinova}, E. and {Ajakan}, H. and {Germain}, P. and {Larochelle}, H. and {Laviolette}, F. and
                  {Marchand}, M. and {Lempitsky}, V.},
  title           = {{Domain-Adversarial Training of Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = may,
  eprint          = {1505.07818},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InCollection{gao2015-are,
  author          = {Gao, Haoyuan and Mao, Junhua and Zhou, Jie and Huang, Zhiheng and Wang, Lei and Xu, Wei},
  title           = {Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2296--2304},
  url             = {http://papers.nips.cc/paper/5641-are-you-talking-to-a-machine-dataset-and-methods-for-multilingual-image-question.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{gao2015-local,
  author          = {Gao, Tian and Ji, Qiang},
  title           = {Local Causal Discovery of Direct Causes and Effects},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2512--2520},
  url             = {http://papers.nips.cc/paper/5974-local-causal-discovery-of-direct-causes-and-effects.pdf},
  timestamp       = {20181201T1030}
}

@Article{gao2017-deepcloak,
  author          = {Gao, Ji and Wang, Beilun and Lin, Zeming and Xu, Weilin and Qi, Yanjun},
  title           = {Deepcloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples},
  journaltitle    = {workshop iclr},
  year            = 2017,
  journal         = {workshop iclr},
  keywords        = {deepcloak, adversarial, redundancy},
  timestamp       = {20181201T1030}
}

@Article{gao2018-black,
  author          = {{Gao}, J. and {Lanchantin}, J. and {Soffa}, M.~L. and {Qi}, Y.},
  title           = {{Black-Box Generation of Adversarial Text Sequences To Evade Deep Learning Classifiers}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.04354},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180104354G},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, text, rnn},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@Article{gardner1988-optimal,
  author          = {Gardner, E and Derrida, B},
  title           = {Optimal Storage Properties of Neural Network Models},
  journaltitle    = {Journal of Physics A: Mathematical and general},
  year            = 1988,
  volume          = 21,
  number          = 1,
  pages           = 271,
  journal         = {Journal of Physics A: Mathematical and general},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1030}
}

@Article{gardner1989-three,
  author          = {Gardner, Elizabeth and Derrida, Bernard},
  title           = {Three Unfinished Works on the Optimal Storage Capacity of Networks},
  journaltitle    = {Journal of Physics A: Mathematical and General},
  year            = 1989,
  volume          = 22,
  number          = 12,
  pages           = 1983,
  journal         = {Journal of Physics A: Mathematical and General},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1030}
}

@Article{gatys2015-neural,
  author          = {{Gatys}, L.~A. and {Ecker}, A.~S. and {Bethge}, M.},
  title           = {{A Neural Algorithm of Artistic Style}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = aug,
  eprint          = {1508.06576},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {style transfer},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@InCollection{gatys2015-texture,
  author          = {Gatys, Leon and Ecker, Alexander S and Bethge, Matthias},
  title           = {Texture Synthesis Using Convolutional Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {262--270},
  url             = {http://papers.nips.cc/paper/5633-texture-synthesis-using-convolutional-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{gatys2016-image,
  author          = {Gatys, Leon A and Ecker, Alexander S and Bethge, Matthias},
  title           = {Image style transfer using convolutional neural networks},
  year            = 2016,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {2414--2423},
  timestamp       = {20181201T1030}
}

@InProceedings{ge2015-escaping,
  author          = {Ge, Rong and Huang, Furong and Jin, Chi and Yuan, Yang},
  title           = {Escaping From Saddle Points-Online Stochastic Gradient for Tensor Decomposition.},
  year            = 2015,
  booktitle       = {COLT},
  pages           = {797--842},
  keywords        = {tensor decomposition, saddle point, non-convex optimization},
  timestamp       = {20181201T1030}
}

@Article{gebru2017-using,
  author          = {{Gebru}, T. and {Krause}, J. and {Wang}, Y. and {Chen}, D. and {Deng}, J. and {Lieberman Aiden}, E. and {Fei-Fei}, L.},
  title           = {{Using Deep Learning and Google Street View To Estimate the Demographic Makeup of the US}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.06683},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@InProceedings{geffet2005-distributional,
  author          = {Geffet, Maayan and Dagan, Ido},
  title           = {The Distributional Inclusion Hypotheses and Lexical Entailment},
  year            = 2005,
  booktitle       = {Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics},
  organization    = {Association for Computational Linguistics},
  pages           = {107--114},
  timestamp       = {20181201T1030}
}

@Article{gehring2016-convolutional,
  author          = {Jonas Gehring and Michael Auli and David Grangier and Yann N. Dauphin},
  title           = {A Convolutional Encoder Model for Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.02344},
  url             = {http://arxiv.org/abs/1611.02344},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GehringAGD16},
  timestamp       = {20181201T1030}
}

@Article{gehring2017-convolutional,
  author          = {{Gehring}, J. and {Auli}, M. and {Grangier}, D. and {Yarats}, D. and {Dauphin}, Y.~N.},
  title           = {{Convolutional Sequence To Sequence Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.03122},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {seq2seq, cnn, translation, nlp},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{geirhos2018-generalisation,
  author          = {Geirhos, Robert and Temme, Carlos RM and Rauber, Jonas and Sch{\"u}tt, Heiko H and Bethge, Matthias and Wichmann, Felix
                  A},
  title           = {Generalisation in humans and deep neural networks},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {7548--7560},
  timestamp       = {20181225T1010}
}

@InProceedings{geirhos2019-imagenet,
  author          = {Robert Geirhos and Patricia Rubisch and Claudio Michaelis and Felix Wichmann and Wieland Brendel and Matthias Bethge},
  title           = {ImageNet-trained {CNN}s are biased towards texture; increasing shape bias improves accuracy and robustness.},
  year            = 2019,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=Bygh9j09KX},
  timestamp       = {20181229T0954}
}

@Book{gelman2013-bayesian,
  author          = {Gelman, Andrew and Stern, Hal S and Carlin, John B and Dunson, David B and Vehtari, Aki and Rubin, Donald B},
  title           = {Bayesian data analysis},
  year            = 2013,
  publisher       = {Chapman and Hall/CRC},
  timestamp       = {20190102T1907}
}

@Article{gemici2017-generative,
  author          = {Gemici, Mevlana and Hung, Chia-Chun and Santoro, Adam and Wayne, Greg and Mohamed, Shakir and Rezende, Danilo J and
                  Amos, David and Lillicrap, Timothy},
  title           = {Generative Temporal Models With Memory},
  journaltitle    = {arXiv preprint arXiv:1702.04649},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.04649},
  keywords        = {planning},
  timestamp       = {20181201T1030}
}

@InProceedings{gers1999-learning,
  author          = {Gers, F.A. and Schmidhuber, J. and Cummins, F.},
  title           = {Learning to forget: continual prediction with LSTM},
  year            = 1999,
  booktitle       = {Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)},
  volume          = 2,
  pages           = {850-855 vol.2},
  doi             = {10.1049/cp:19991218},
  url             = {https://doi.org/10.1049/cp:19991218},
  issn            = {0537-9989},
  keywords        = {recurrent neural nets;adaptive forget gate;learning;long short-term memory;recurrent neural networks;resource
                  allocation},
  timestamp       = {20181201T1030}
}

@Article{gillick2015-multilingual,
  author          = {Dan Gillick and Cliff Brunk and Oriol Vinyals and Amarnag Subramanya},
  title           = {Multilingual Language Processing From Bytes},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.00103},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{gilmer2018-adversarial,
  author          = {{Gilmer}, J. and {Metz}, L. and {Faghri}, F. and {Schoenholz}, S.~S. and {Raghu}, M. and {Wattenberg}, M. and
                  {Goodfellow}, I.},
  title           = {{Adversarial Spheres}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.02774},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180102774G},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, hypothesis},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@InProceedings{girshick2014-rich,
  author          = {Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
  title           = {Rich feature hierarchies for accurate object detection and semantic segmentation},
  year            = 2014,
  booktitle       = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages           = {580--587},
  timestamp       = {20181201T1030}
}

@InProceedings{girshick2015-fast,
  author          = {Girshick, Ross},
  title           = {Fast r-cnn},
  year            = 2015,
  booktitle       = {Proceedings of the IEEE International Conference on Computer Vision},
  pages           = {1440--1448},
  timestamp       = {20181201T1030}
}

@Article{gliozzi2018-self,
  author          = {{Gliozzi}, V. and {Plunkett}, K.},
  title           = {{Self-Organizing Maps and Generalization: an Algorithmic Description of Numerosity and Variability Effects}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.09442},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180209442G},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Quantitative Biology - Neurons and Cognition},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@InProceedings{globerson2006-nightmare,
  author          = {Globerson, Amir and Roweis, Sam},
  title           = {Nightmare at test time: robust learning by feature deletion},
  year            = 2006,
  booktitle       = {Proceedings of the 23rd international conference on Machine learning},
  organization    = {ACM},
  pages           = {353--360},
  timestamp       = {20181201T1030}
}

@InProceedings{glorot2010-understanding,
  author          = {Glorot, Xavier and Bengio, Yoshua},
  title           = {Understanding the difficulty of training deep feedforward neural networks},
  year            = 2010,
  booktitle       = {International conference on artificial intelligence and statistics},
  pages           = {249--256},
  timestamp       = {20181201T1030}
}

@InProceedings{glorot2011-deep,
  author          = {Xavier Glorot and Antoine Bordes and Yoshua Bengio},
  title           = {Deep Sparse Rectifier Neural Networks},
  year            = 2011,
  booktitle       = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11)},
  editor          = {Geoffrey J. Gordon and David B. Dunson},
  volume          = 15,
  publisher       = {Journal of Machine Learning Research - Workshop and Conference Proceedings},
  pages           = {315-323},
  url             = {http://www.jmlr.org/proceedings/papers/v15/glorot11a/glorot11a.pdf},
  timestamp       = {20181201T1030}
}

@Article{goel2014-learning,
  author          = {Kratarth Goel and Raunaq Vohra},
  title           = {Learning Temporal Dependencies in Data Using a {DBN-BLSTM}},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6093},
  url             = {http://arxiv.org/abs/1412.6093},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GoelV14},
  timestamp       = {20181201T1030}
}

@Article{goldberg2014-word2vec,
  author          = {Yoav Goldberg and Omer Levy},
  title           = {Word2vec Explained: Deriving Mikolov Et Al.'s Negative-Sampling Word-Embedding Method},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1402.3722},
  url             = {http://arxiv.org/abs/1402.3722},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GoldbergL14},
  keywords        = {word2vec},
  timestamp       = {20181201T1030}
}

@InCollection{goldberger2005-neighbourhood,
  author          = {Jacob Goldberger and Geoffrey E. Hinton and Sam T. Roweis and Salakhutdinov, Ruslan R},
  title           = {Neighbourhood Components Analysis},
  year            = 2005,
  booktitle       = {Advances in Neural Information Processing Systems 17},
  editor          = {L. K. Saul and Y. Weiss and L. Bottou},
  publisher       = {MIT Press},
  pages           = {513--520},
  url             = {http://papers.nips.cc/paper/2566-neighbourhood-components-analysis.pdf},
  timestamp       = {20181201T1030}
}

@Article{goldman2007-neural,
  author          = {Goldman, M and Compte, A and Wang, XJ},
  title           = {Neural Integrators: Recurrent Mechanisms and Models},
  journaltitle    = {New Encyclopedia of Neuroscience},
  year            = 2007,
  pages           = {1--26},
  journal         = {New Encyclopedia of Neuroscience},
  timestamp       = {20181201T1030}
}

@Article{golea1996-learning,
  author          = {Golea, Mostefa and Marchand, Mario and Hancock, Thomas R},
  title           = {On Learning $\mu$-perceptron Networks on the Uniform Distribution},
  journaltitle    = {Neural Networks},
  year            = 1996,
  volume          = 9,
  number          = 1,
  pages           = {67--82},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{gomez1997-incremental,
  author          = {Gomez, Faustino and Miikkulainen, Risto},
  title           = {Incremental Evolution of Complex General Behavior},
  journaltitle    = {Adaptive Behavior},
  year            = 1997,
  volume          = 5,
  number          = {3-4},
  pages           = {317--342},
  journal         = {Adaptive Behavior},
  publisher       = {Sage Publications},
  timestamp       = {20181201T1030}
}

@InProceedings{gomez1999-solving,
  author          = {Gomez, Faustino J and Miikkulainen, Risto},
  title           = {Solving non-Markovian control tasks with neuroevolution},
  year            = 1999,
  booktitle       = {IJCAI},
  volume          = 99,
  pages           = {1356--1361},
  timestamp       = {20181201T1030}
}

@InProceedings{gomez2005-co,
  author          = {Gomez, Faustino J. and Schmidhuber, J{\"u}rgen},
  title           = {Co-evolving Recurrent Neurons Learn Deep Memory POMDPs},
  year            = 2005,
  booktitle       = {Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation},
  series          = {GECCO '05},
  publisher       = {ACM},
  location        = {Washington DC, USA},
  isbn            = {1-59593-010-8},
  pages           = {491--498},
  doi             = {10.1145/1068009.1068092},
  url             = {https://doi.org/10.1145/1068009.1068092},
  acmid           = 1068092,
  address         = {New York, NY, USA},
  keywords        = {POMDP, coevolution, recurrent neural networks},
  numpages        = 8,
  timestamp       = {20181201T1030}
}

@InProceedings{gomez2005-evolving,
  author          = {Gomez, Faustino and Schmidhuber, J{\"u}rgen},
  title           = {Evolving Modular Fast-weight Networks for Control},
  year            = 2005,
  booktitle       = {Proceedings of the 15th International Conference on Artificial Neural Networks: Formal Models and Their Applications -
                  Volume Part II},
  series          = {ICANN'05},
  publisher       = {Springer-Verlag},
  location        = {Warsaw, Poland},
  isbn            = {3-540-28755-8, 978-3-540-28755-1},
  pages           = {383--389},
  url             = {http://dl.acm.org/citation.cfm?id=1986079.1986149},
  acmid           = 1986149,
  address         = {Berlin, Heidelberg},
  numpages        = 7,
  timestamp       = {20181201T1030}
}

@Article{gomez2008-accelerated,
  author          = {Gomez, Faustino and Schmidhuber, J{\"u}rgen and Miikkulainen, Risto},
  title           = {Accelerated Neural Evolution Through Cooperatively Coevolved Synapses},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2008,
  volume          = 9,
  number          = {May},
  pages           = {937--965},
  journal         = {Journal of Machine Learning Research},
  timestamp       = {20181201T1030}
}

@InCollection{gomez2017-reversible,
  author          = {Gomez, Aidan N and Ren, Mengye and Urtasun, Raquel and Grosse, Roger B},
  title           = {The Reversible Residual Network: Backpropagation Without Storing Activations},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2211--2221},
  url             = {http://papers.nips.cc/paper/6816-the-reversible-residual-network-backpropagation-without-storing-activations.pdf},
  timestamp       = {20181201T1030}
}

@Article{gondara2017-detecting,
  author          = {Gondara, Lovedeep},
  title           = {Detecting Adversarial Samples Using Density Ratio Estimates},
  journaltitle    = {arXiv preprint arXiv:1705.02224},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.02224},
  keywords        = {adversarial, density ratio},
  timestamp       = {20181201T1030}
}

@Article{gong2013-iterative,
  author          = {Gong, Yunchao and Lazebnik, Svetlana and Gordo, Albert and Perronnin, Florent},
  title           = {Iterative Quantization: a Procrustean Approach To Learning Binary Codes for Large-Scale Image Retrieval},
  journaltitle    = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year            = 2013,
  volume          = 35,
  number          = 12,
  pages           = {2916--2929},
  journal         = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{gong2014-compressing,
  author          = {Gong, Yunchao and Liu, Liu and Yang, Ming and Bourdev, Lubomir},
  title           = {Compressing Deep Convolutional Networks Using Vector Quantization},
  journaltitle    = {arXiv preprint arXiv:1412.6115},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1412.6115},
  keywords        = {quantization, codebook, kmeans, product quantization, residual quantization},
  timestamp       = {20181201T1030}
}

@Article{gong2017-adversarial,
  author          = {Zhitao Gong and Wenlu Wang and Wei{-}Shinn Ku},
  title           = {Adversarial and Clean Data Are Not Twins},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.04960},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InCollection{goodfellow2009-measuring,
  author          = {Goodfellow, Ian and Lee, Honglak and Quoc V. Le and Andrew Saxe and Andrew Y. Ng},
  title           = {Measuring Invariances in Deep Networks},
  year            = 2009,
  booktitle       = {Advances in Neural Information Processing Systems 22},
  editor          = {Y. Bengio and D. Schuurmans and J. D. Lafferty and C. K. I. Williams and A. Culotta},
  publisher       = {Curran Associates, Inc.},
  pages           = {646--654},
  url             = {http://papers.nips.cc/paper/3790-measuring-invariances-in-deep-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{goodfellow2013-empirical,
  author          = {Goodfellow, Ian J and Mirza, Mehdi and Xiao, Da and Courville, Aaron and Bengio, Yoshua},
  title           = {An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks},
  journaltitle    = {arXiv preprint arXiv:1312.6211},
  year            = 2013,
  journal         = {arXiv preprint arXiv:1312.6211},
  keywords        = {continual learning, forgetting},
  timestamp       = {20181201T1030}
}

@Article{goodfellow2013-maxout,
  author          = {{Goodfellow}, I.~J. and {Warde-Farley}, D. and {Mirza}, M. and {Courville}, A. and {Bengio}, Y.},
  title           = {{Maxout Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2013,
  month           = feb,
  eprint          = {1302.4389},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{goodfellow2014-explaining,
  author          = {{Goodfellow}, I.~J. and {Shlens}, J. and {Szegedy}, C.},
  title           = {{Explaining and Harnessing Adversarial Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = dec,
  eprint          = {1412.6572},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, fgsm, adversarial training},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{goodfellow2014-generative,
  author          = {{Goodfellow}, I.~J. and {Pouget-Abadie}, J. and {Mirza}, M. and {Xu}, B. and {Warde-Farley}, D. and {Ozair}, S. and
                  {Courville}, A. and {Bengio}, Y.},
  title           = {{Generative Adversarial Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = jun,
  eprint          = {1406.2661},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {gan},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{goodfellow2014-qualitatively,
  author          = {Ian J. Goodfellow and Oriol Vinyals},
  title           = {Qualitatively Characterizing Neural Network Optimization Problems},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6544},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{goodfellow2017-nips,
  author          = {{Goodfellow}, I.},
  title           = {{NIPS 2016 Tutorial: Generative Adversarial Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1701.00160},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{goodman2001-classes,
  author          = {Joshua Goodman},
  title           = {Classes for Fast Maximum Entropy Training},
  journaltitle    = {CoRR},
  year            = 2001,
  volume          = {cs.CL/0108006},
  url             = {http://arxiv.org/abs/cs.CL/0108006},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/cs-CL-0108006},
  timestamp       = {20181201T1030}
}

@InProceedings{goroshin2015-learning,
  author          = {Goroshin, Ross and Mathieu, Michael F and LeCun, Yann},
  title           = {Learning to linearize under uncertainty},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {1234--1242},
  timestamp       = {20181229T1021}
}

@Article{goyal2017-accurate,
  author          = {Priya Goyal and Piotr Doll{\'{a}}r and Ross B. Girshick and Pieter Noordhuis and Lukasz Wesolowski and Aapo Kyrola and
                  Andrew Tulloch and Yangqing Jia and Kaiming He},
  title           = {Accurate, Large Minibatch {SGD:} Training Imagenet in 1 Hour},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.02677},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{grace2017-when,
  author          = {{Grace}, K. and {Salvatier}, J. and {Dafoe}, A. and {Zhang}, B. and {Evans}, O.},
  title           = {{When Will Ai Exceed Human Performance? Evidence From Ai Experts}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.08807},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Computers and Society},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@Article{grave2016-efficient,
  author          = {Edouard Grave and Armand Joulin and Moustapha Ciss{\'{e}} and David Grangier and Herv{\'{e}} J{\'{e}}gou},
  title           = {Efficient Softmax Approximation for Gpus},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.04309},
  url             = {http://arxiv.org/abs/1609.04309},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GraveJCGJ16},
  timestamp       = {20181201T1030}
}

@InCollection{grave2017-unbounded,
  author          = {Grave, Edouard and Cisse, Moustapha M and Joulin, Armand},
  title           = {Unbounded cache model for online language modeling with open vocabulary},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6044--6054},
  url             = {http://papers.nips.cc/paper/7185-unbounded-cache-model-for-online-language-modeling-with-open-vocabulary.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{graves2011-practical,
  author          = {Graves, Alex},
  title           = {Practical variational inference for neural networks},
  year            = 2011,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {2348--2356},
  keywords        = {pruning, variational, bayesian},
  timestamp       = {20181201T1030}
}

@Book{graves2012-supervised,
  author          = {Graves, Alex and others},
  title           = {Supervised sequence labelling with recurrent neural networks},
  year            = 2012,
  volume          = 385,
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{graves2013-generating,
  author          = {Alex Graves},
  title           = {Generating Sequences With Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1308.0850},
  url             = {http://arxiv.org/abs/1308.0850},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Graves13},
  timestamp       = {20181201T1030}
}

@Article{graves2014-neural,
  author          = {Alex Graves and Greg Wayne and Ivo Danihelka},
  title           = {Neural Turing Machines},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1410.5401},
  url             = {http://arxiv.org/abs/1410.5401},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GravesWD14},
  timestamp       = {20181201T1030}
}

@Article{graves2016-hybrid,
  author          = "Graves, Alex and Wayne, Greg and Reynolds, Malcolm and Harley, Tim and Danihelka, Ivo and Grabska-Barwi??ska, Agnieszka
                  and Colmenarejo, Sergio G??mez and Grefenstette, Edward and Ramalho, Tiago and Agapiou, John and Badia, Adri??
                  Puigdom?{\textasciidieresis}nech and Hermann, Karl Moritz and Zwols, Yori and Ostrovski, Georg and Cain, Adam and King,
                  Helen and Summerfield, Christopher and Blunsom, Phil and Kavukcuoglu, Koray and Hassabis, Demis",
  title           = {Hybrid Computing Using a Neural Network With Dynamic External Memory},
  journaltitle    = "Nature",
  year            = 2016,
  volume          = "advance online publication",
  month           = "Oct",
  note            = "Article",
  issn            = "1476-4687",
  url             = "http://dx.doi.org/10.1038/nature20101",
  journal         = "Nature",
  day             = 12,
  publisher       = "Macmillan Publishers Limited, part of Springer Nature. All rights reserved.",
  timestamp       = {20181201T1030}
}

@Article{grefenstette2015-learning,
  author          = {Edward Grefenstette and Karl Moritz Hermann and Mustafa Suleyman and Phil Blunsom},
  title           = {Learning To Transduce With Unbounded Memory},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.02516},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{greff2016-tagger,
  author          = {{Greff}, K. and {Rasmus}, A. and {Berglund}, M. and {Hotloo Hao}, T. and {Schmidhuber}, J. and {Valpola}, H.},
  title           = {{Tagger: Deep Unsupervised Perceptual Grouping}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.06724},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Neural and Evolutionary Computing,
                  97R40},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{gregor2016-towards,
  author          = {{Gregor}, K. and {Besse}, F. and {Jimenez Rezende}, D. and {Danihelka}, I. and {Wierstra}, D.},
  title           = {{Towards Conceptual Compression}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = apr,
  eprint          = {1604.08772},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2016arXiv160408772G},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Book{grenander2012-calculus,
  author          = {Grenander, Ulf},
  title           = {A Calculus of Ideas: A Mathematical Study of Human Thought},
  year            = 2012,
  publisher       = {World Scientific},
  timestamp       = {20190104T0927}
}

@Article{grewal2017-variance,
  author          = {{Grewal}, K. and {Devon Hjelm}, R and {Bengio}, Y.},
  title           = {{Variance Regularizing Adversarial Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.00309},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Book{griffiths2016-introduction,
  author          = {Griffiths, David J},
  title           = {Introduction to quantum mechanics},
  year            = 2016,
  publisher       = {Cambridge University Press},
  timestamp       = {20181201T1030}
}

@Article{grossberg1987-competitive,
  author          = {Grossberg, Stephen},
  title           = {Competitive Learning: From Interactive Activation To Adaptive Resonance},
  journaltitle    = {Cognitive science},
  year            = 1987,
  volume          = 11,
  number          = 1,
  pages           = {23--63},
  journal         = {Cognitive science},
  publisher       = {Wiley Online Library},
  timestamp       = {20181201T1030}
}

@Article{grosse2016-adversarial,
  author          = {Kathrin Grosse and Nicolas Papernot and Praveen Manoharan and Michael Backes and Patrick McDaniel},
  title           = {Adversarial Perturbations Against Deep Neural Networks for Malware Classification},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.04435},
  url             = {http://arxiv.org/abs/1606.04435},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GrossePM0M16},
  keywords        = {adversarial, attack},
  timestamp       = {20181201T1030}
}

@Article{grosse2017-detection,
  author          = {Grosse, Kathrin and Manoharan, Praveen and Papernot, Nicolas and Backes, Michael and McDaniel, Patrick},
  title           = {On the (statistical) Detection of Adversarial Examples},
  journaltitle    = {arXiv preprint arXiv:1702.06280},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.06280},
  timestamp       = {20181201T1030}
}

@Article{grossman1989-chir,
  author          = {Grossman, Tal},
  title           = {The Chir Algorithm: a Generalization for Multiple-Output and Multi-Layered Networks},
  journaltitle    = {Complex Systems},
  year            = 1989,
  volume          = 3,
  pages           = {407--419},
  journal         = {Complex Systems},
  timestamp       = {20181201T1030}
}

@Article{grover2017-boosted,
  author          = {Aditya Grover and Stefano Ermon},
  title           = {Boosted Generative Models},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1702.08484},
  url             = {http://arxiv.org/abs/1702.08484},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GroverE17},
  timestamp       = {20181201T1030}
}

@InProceedings{gruau1992-genetic,
  author          = {F. Gruau},
  title           = {Genetic synthesis of Boolean neural networks with a cell rewriting developmental process},
  year            = 1992,
  booktitle       = {Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92. International Workshop on},
  month           = {Jun},
  pages           = {55-74},
  doi             = {10.1109/COGANN.1992.273948},
  url             = {https://doi.org/10.1109/COGANN.1992.273948},
  keywords        = {Boolean functions;encoding;genetic algorithms;grammars;neural nets;rewriting systems;40 inputs symmetry function;50
                  inputs parity function;Boolean functions;Boolean neural networks;cell rewriting developmental process;cell rewriting
                  grammar;genetic algorithms;genetic synthesis;scalability property;Biological cells;Boolean functions;Cells
                  (biology);Electronic mail;Encoding;Genetic algorithms;Network synthesis;Neural networks;Neurons;Scalability},
  timestamp       = {20181201T1030}
}

@Article{gruau1993-adding,
  author          = {F. Gruau and D. Whitley},
  title           = {Adding Learning To the Cellular Development of Neural Networks: Evolution and the Baldwin Effect},
  journaltitle    = {Evolutionary Computation},
  year            = 1993,
  volume          = 1,
  number          = 3,
  month           = {Sept},
  pages           = {213-233},
  issn            = {1063-6560},
  doi             = {10.1162/evco.1993.1.3.213},
  url             = {https://doi.org/10.1162/evco.1993.1.3.213},
  journal         = {Evolutionary Computation},
  keywords        = {cellular encoding;genetic algorithms;learning developmental system;neural networks},
  timestamp       = {20181201T1030}
}

@Misc{gruau1994-neural,
  author          = {Gruau, Frederic and others},
  title           = {Neural Network Synthesis Using Cellular Encoding and the Genetic Algorithm},
  year            = 1994,
  publisher       = {Citeseer},
  timestamp       = {20181201T1030}
}

@Book{gruenwald2007-minimum,
  author          = {Gr{\"u}nwald, Peter D},
  title           = {The Minimum Description Length Principle},
  year            = 2007,
  publisher       = {MIT press},
  timestamp       = {20181201T1030}
}

@Article{gu2014-towards,
  author          = {Shixiang Gu and Luca Rigazio},
  title           = {Towards Deep Neural Network Architectures Robust To Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.5068},
  url             = {http://arxiv.org/abs/1412.5068},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GuR14},
  keywords        = {adversarial, contractive penalty, dae, cae, autoencoder, recover},
  timestamp       = {20181201T1030}
}

@Article{gu2016-incorporating,
  author          = {Jiatao Gu and Zhengdong Lu and Hang Li and Victor O. K. Li},
  title           = {Incorporating Copying Mechanism in Sequence-To-Sequence Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.06393},
  url             = {http://arxiv.org/abs/1603.06393},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/GuLLL16},
  timestamp       = {20181201T1030}
}

@Article{gu2017-neural,
  author          = {{Gu}, J. and {Jiwoong Im}, D. and {Li}, V.~O.~K.},
  title           = {{Neural Machine Translation With Gumbel-Greedy Decoding}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.07518},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {gumbel, nmt, gan},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InCollection{gueant2011-mean,
  author          = {Gu{\'e}ant, Olivier and Lasry, Jean-Michel and Lions, Pierre-Louis},
  title           = {Mean field games and applications},
  year            = 2011,
  booktitle       = {Paris-Princeton lectures on mathematical finance 2010},
  publisher       = {Springer},
  pages           = {205--266},
  timestamp       = {20181201T1030}
}

@Article{guergiuev2016-towards,
  author          = {{Guergiuev}, J. and {Lillicrap}, T.~P. and {Richards}, B.~A.},
  title           = {{Towards Deep Learning With Segregated dendrites}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = oct,
  eprint          = {1610.00161},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Quantitative Biology - Neurons and Cognition},
  primaryclass    = "q-bio.NC",
  timestamp       = {20181201T1030}
}

@Article{gulcehre2016-noisy,
  author          = {{Gulcehre}, C. and {Moczulski}, M. and {Denil}, M. and {Bengio}, Y.},
  title           = {{Noisy Activation Functions}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = mar,
  eprint          = {1603.00391},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{gulcehre2017-integrating,
  author          = "Caglar Gulcehre and Orhan Firat and Kelvin Xu and Kyunghyun Cho and Yoshua Bengio",
  title           = {On Integrating a Language Model Into Neural Machine Translation},
  journaltitle    = "Computer Speech \& Language",
  year            = 2017,
  issn            = "0885-2308",
  doi             = {10.1016/j.csl.2017.01.014},
  url             = {https://doi.org/10.1016/j.csl.2017.01.014},
  journal         = "Computer Speech \& Language",
  timestamp       = {20181201T1030}
}

@Article{gulcehre2017-memory,
  author          = {{Gulcehre}, C. and {Chandar}, S. and {Bengio}, Y.},
  title           = {{Memory Augmented Neural Networks With Wormhole Connections}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jan,
  eprint          = {1701.08718},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{gulcehre2017-plan,
  author          = {{Gulcehre}, C. and {Dutil}, F. and {Trischler}, A. and {Bengio}, Y.},
  title           = {{Plan, Attend, Generate: Character-Level Neural Machine Translation With Planning in the Decoder}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.05087},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{guo2014-learning,
  author          = {Jiang Guo and Wanxiang Che and Haifeng Wang and Ting Liu},
  title           = {Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources},
  year            = 2014,
  booktitle       = {COLING},
  timestamp       = {20181201T1030}
}

@Article{guo2015-cnn,
  author          = {Jinma Guo and Jianmin Li},
  title           = {{CNN} Based Hashing for Image Retrieval},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1509.01354},
  journal         = {CoRR},
  keywords        = {index},
  timestamp       = {20181201T1030}
}

@Article{guo2015-generating,
  author          = {{Guo}, H.},
  title           = {{Generating Text With Deep Reinforcement Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = oct,
  eprint          = {1510.09202},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Learning, Computer Science - Neural and Evolutionary
                  Computing},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{guo2016-dynamic,
  author          = {Guo, Yiwen and Yao, Anbang and Chen, Yurong},
  title           = {Dynamic Network Surgery for Efficient DNNs},
  year            = 2016,
  booktitle       = {Advances In Neural Information Processing Systems},
  pages           = {1379--1387},
  keywords        = {pruning},
  timestamp       = {20181201T1030}
}

@Article{guo2017-countering,
  author          = {{Guo}, C. and {Rana}, M. and {Cisse}, M. and {van der Maaten}, L.},
  title           = {{Countering Adversarial Images Using Input Transformations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1711.00117},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171100117G},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense, image, quilting},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{guo2017-long,
  author          = {{Guo}, J. and {Lu}, S. and {Cai}, H. and {Zhang}, W. and {Yu}, Y. and {Wang}, J.},
  title           = {{Long Text Generation Via Adversarial Training With Leaked Information}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = sep,
  eprint          = {1709.08624},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{guo2017-network,
  author          = {Guo, Yiwen and Yao, Anbang and Zhao, Hao and Chen, Yurong},
  title           = {Network sketching: Exploiting binary structure in deep cnns},
  year            = 2017,
  booktitle       = {IEEE Conference on Computer Vision and Pattern Recognition},
  volume          = 2,
  keywords        = {quant},
  timestamp       = {20181201T1030}
}

@Article{gupta2015-deep,
  author          = {Gupta, Suyog and Agrawal, Ankur and Gopalakrishnan, Kailash and Narayanan, Pritish},
  title           = {Deep Learning With Limited Numerical Precision},
  journaltitle    = {CoRR, abs/1502.02551},
  year            = 2015,
  volume          = 392,
  journal         = {CoRR, abs/1502.02551},
  keywords        = {quantization},
  timestamp       = {20181201T1030}
}

@Article{gutfreund1990-capacity,
  author          = {Gutfreund, Hanoch and Stein, Yaakov},
  title           = {Capacity of Neural Networks With Discrete Synaptic Couplings},
  journaltitle    = {Journal of Physics A: Mathematical and General},
  year            = 1990,
  volume          = 23,
  number          = 12,
  pages           = 2613,
  journal         = {Journal of Physics A: Mathematical and General},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1030}
}

@Article{ha2016-hypernetworks,
  author          = {David Ha and Andrew M. Dai and Quoc V. Le},
  title           = {Hypernetworks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.09106},
  eprint          = {1609.09106},
  url             = {http://arxiv.org/abs/1609.09106},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/HaDL16},
  timestamp       = {20181201T1030}
}

@Article{ha2017-neural,
  author          = {David Ha and Douglas Eck},
  title           = {A Neural Representation of Sketch Drawings},
  keywords        = {sketch rnn, quickdraw, autodraw},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.03477},
  eprint          = {1704.03477},
  url             = {http://arxiv.org/abs/1704.03477},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/HaE17},
  timestamp       = {20181230T1442}
}

@Article{ha2018-world,
  author          = {{Ha}, D. and {Schmidhuber}, J.},
  title           = {{World Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = mar,
  eprint          = {1803.10122},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180310122H},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{haarnoja2017-reinforcement,
  author          = {Tuomas Haarnoja and Haoran Tang and Pieter Abbeel and Sergey Levine},
  title           = {Reinforcement Learning With Deep Energy-Based Policies},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1702.08165},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InProceedings{hadjis2015-caffe,
  author          = {Hadjis, Stefan and Abuzaid, Firas and Zhang, Ce and R{\'e}, Christopher},
  title           = {Caffe Con Troll: Shallow Ideas to Speed Up Deep Learning},
  year            = 2015,
  booktitle       = {Proceedings of the Fourth Workshop on Data Analytics in the Cloud},
  series          = {DanaC'15},
  publisher       = {ACM},
  location        = {Melbourne, VIC, Australia},
  isbn            = {978-1-4503-3724-3},
  pages           = {2:1--2:4},
  doi             = {10.1145/2799562.2799641},
  url             = {https://doi.org/10.1145/2799562.2799641},
  acmid           = 2799641,
  address         = {New York, NY, USA},
  articleno       = 2,
  numpages        = 4,
  timestamp       = {20181201T1030}
}

@Article{han2015-deep,
  author          = {Song Han and Huizi Mao and William J. Dally},
  title           = {Deep Compression: Compressing Deep Neural Network With Pruning, Trained Quantization and Huffman Coding},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1510.00149},
  url             = {http://arxiv.org/abs/1510.00149},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HanMD15},
  keywords        = {compression, quantization, pruning, mnist, imagenet},
  timestamp       = {20181201T1030}
}

@InCollection{han2015-learning,
  author          = {Han, Song and Pool, Jeff and Tran, John and Dally, William},
  title           = {Learning both Weights and Connections for Efficient Neural Network},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1135--1143},
  url             = {http://papers.nips.cc/paper/5784-learning-both-weights-and-connections-for-efficient-neural-network.pdf},
  keywords        = {compression, pruning, imagenet, cnn},
  timestamp       = {20181201T1030}
}

@Article{han2016-ese,
  author          = {Han, Song and Kang, Junlong and Mao, Huizi and Hu, Yiming and Li, Xin and Li, Yubin and Xie, Dongliang and Luo, Hong
                  and Yao, Song and Wang, Yu and others},
  title           = {Ese: Efficient Speech Recognition Engine With Compressed Lstm on Fpga},
  journaltitle    = {arXiv preprint arXiv:1612.00694},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1612.00694},
  keywords        = {lstm, compression, fpga, ese, rnn, prune},
  timestamp       = {20181201T1030}
}

@InProceedings{han2017-alternating,
  author          = {Han, Tian and Lu, Yang and Zhu, Song-Chun and Wu, Ying Nian},
  title           = {Alternating Back-Propagation for Generator Network},
  year            = 2017,
  booktitle       = {AAAI},
  pages           = {1976--1984},
  timestamp       = {20181201T1030}
}

@Article{hansen2016-cma,
  author          = {Nikolaus Hansen},
  title           = {The {CMA} Evolution Strategy: {A} Tutorial},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.00772},
  eprint          = {1604.00772},
  url             = {http://arxiv.org/abs/1604.00772},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/Hansen16a},
  keywords        = {evolution, cma},
  timestamp       = {20181201T1030}
}

@InCollection{hanson1989-comparing,
  author          = {Stephen Jose Hanson and Lorien Y. Pratt},
  title           = {Comparing Biases for Minimal Network Construction with Back-Propagation},
  year            = 1989,
  booktitle       = {Advances in Neural Information Processing Systems 1},
  editor          = {D. S. Touretzky},
  publisher       = {Morgan-Kaufmann},
  pages           = {177--185},
  url             = {http://papers.nips.cc/paper/156-comparing-biases-for-minimal-network-construction-with-back-propagation.pdf},
  keywords        = {pruning},
  timestamp       = {20181201T1030}
}

@InProceedings{hara2018-can,
  author          = {Hara, Kensho and Kataoka, Hirokatsu and Satoh, Yutaka},
  title           = {Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet},
  year            = 2018,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA},
  pages           = {18--22},
  timestamp       = {20181211T1311}
}

@Article{harmon1996-reinforcement,
  author          = {Harmon, Mance E and Harmon, Stephanie S},
  title           = {Reinforcement Learning: a Tutorial},
  journaltitle    = {WL/AAFC, WPAFB Ohio},
  year            = 1996,
  volume          = 45433,
  journal         = {WL/AAFC, WPAFB Ohio},
  timestamp       = {20181201T1030}
}

@InProceedings{harp1989-towards,
  author          = {Harp, Steven Alex and Samad, Tariq and Guha, Aloke},
  title           = {Towards the Genetic Synthesis of Neural Network},
  year            = 1989,
  booktitle       = {Proceedings of the Third International Conference on Genetic Algorithms},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  location        = {George Mason University, USA},
  isbn            = {1-55860-006-3},
  pages           = {360--369},
  url             = {http://dl.acm.org/citation.cfm?id=93126.93260},
  acmid           = 93260,
  address         = {San Francisco, CA, USA},
  numpages        = 10,
  timestamp       = {20181201T1030}
}

@InProceedings{harp1990-designing,
  author          = {Harp, Steven A and Samad, Tariq and Guha, Aloke},
  title           = {Designing application-specific neural networks using the genetic algorithm},
  year            = 1990,
  booktitle       = {Advances in neural information processing systems},
  pages           = {447--454},
  timestamp       = {20181201T1030}
}

@Article{harp1991-genetic,
  author          = {Harp, Steven Alex and Samad, Tariq},
  title           = {Genetic Synthesis of Neural Network Architecture},
  journaltitle    = {Handbook of genetic algorithms},
  year            = 1991,
  pages           = {202--221},
  journal         = {Handbook of genetic algorithms},
  timestamp       = {20181201T1030}
}

@Article{harper2016-movielens,
  author          = {Harper, F Maxwell and Konstan, Joseph A},
  title           = {The Movielens Datasets: History and Context},
  journaltitle    = {Acm transactions on interactive intelligent systems (tiis)},
  year            = 2016,
  volume          = 5,
  number          = 4,
  pages           = 19,
  journal         = {Acm transactions on interactive intelligent systems (tiis)},
  keywords        = {data, movielens},
  publisher       = {ACM},
  timestamp       = {20181201T1030}
}

@Article{hassabis2017-neuroscience,
  author          = {Hassabis, Demis and Kumaran, Dharshan and Summerfield, Christopher and Botvinick, Matthew},
  title           = {Neuroscience-Inspired Artificial Intelligence},
  journaltitle    = {Neuron},
  year            = 2017,
  volume          = 95,
  number          = 2,
  pages           = {245--258},
  journal         = {Neuron},
  keywords        = {survey, ai, neuroscience},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@InProceedings{hassan2018-achieving,
  author          = {Hassan Awadalla, Hany and Aue, Anthony and Chen, Chang and Chowdhary, Vishal and Clark, Jonathan and Federmann,
                  Christian and Huang, Xuedong and Junczys-Dowmunt, Marcin and Lewis, Will and Li, Mu and Liu, Shujie and Liu, Tie-Yan and
                  Luo, Renqian and Menezes, Arul and Qin, Tao and Seide, Frank and Tan, Xu and Tian, Fei and Wu, Lijun and Wu, Shuangzhi and
                  Xia, Yingce and Zhang, Dongdong and Zhang, Zhirui and Zhou, Ming},
  title           = {Achieving Human Parity on Automatic Chinese to English News Translation},
  year            = 2018,
  booktitle       = {MS Research},
  month           = {March},
  url             = {https://www.microsoft.com/en-us/research/publication/achieving-human-parity-on-automatic-chinese-to-english-news-translation/},
  timestamp       = {20181201T1030}
}

@Article{hasselt2015-deep,
  author          = {Hado van Hasselt and Arthur Guez and David Silver},
  title           = {Deep Reinforcement Learning With Double Q-Learning},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1509.06461},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InProceedings{hassibi1993-optimal,
  author          = {Hassibi, Babak and Stork, David G and Wolff, Gregory J},
  title           = {Optimal brain surgeon and general network pruning},
  year            = 1993,
  booktitle       = {Neural Networks, 1993., IEEE International Conference on},
  organization    = {IEEE},
  pages           = {293--299},
  keywords        = {compression, pruning},
  timestamp       = {20181201T1030}
}

@Article{hassibi1993-second,
  author          = {Hassibi, Babak and Stork, David G and others},
  title           = {Second Order Derivatives for Network Pruning: Optimal Brain Surgeon},
  journaltitle    = {Advances in neural information processing systems},
  year            = 1993,
  pages           = {164--164},
  journal         = {Advances in neural information processing systems},
  keywords        = {pruning},
  publisher       = {Morgan Kaufmann Publishers},
  timestamp       = {20181201T1030}
}

@InCollection{hauser2017-principles,
  author          = {Hauser, Michael and Ray, Asok},
  title           = {Principles of Riemannian Geometry in Neural Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2804--2813},
  url             = {http://papers.nips.cc/paper/6873-principles-of-riemannian-geometry-in-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{hayes2017-machine,
  author          = {Hayes, Jamie and Danezis, George},
  title           = {Machine Learning As an Adversarial Service: Learning Black-Box Adversarial Examples},
  journaltitle    = {arXiv preprint arXiv:1708.05207},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1708.05207},
  timestamp       = {20181201T1030}
}

@Article{hazan2017-hyperparameter,
  author          = {{Hazan}, E. and {Klivans}, A. and {Yuan}, Y.},
  title           = {{Hyperparameter Optimization: a Spectral Approach}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.00764},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {discrete},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{he2015-deep-reinforcement,
  author          = {Ji He and Jianshu Chen and Xiaodong He and Jianfeng Gao and Lihong Li and Li Deng and Mari Ostendorf},
  title           = {Deep Reinforcement Learning With an Unbounded Action Space},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.04636},
  url             = {http://arxiv.org/abs/1511.04636},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HeCHGLDO15},
  timestamp       = {20181201T1030}
}

@Article{he2015-deep-residual,
  author          = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
  title           = {Deep Residual Learning for Image Recognition},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.03385},
  url             = {http://arxiv.org/abs/1512.03385},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HeZRS15},
  keywords        = {resnet50},
  timestamp       = {20181201T1030}
}

@InProceedings{he2015-delving,
  author          = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  title           = {Delving deep into rectifiers: Surpassing human-level performance on imagenet classification},
  year            = 2015,
  booktitle       = {Proceedings of the IEEE international conference on computer vision},
  pages           = {1026--1034},
  timestamp       = {20181201T1030}
}

@InProceedings{he2016-dual,
  author          = {He, Di and Xia, Yingce and Qin, Tao and Wang, Liwei and Yu, Nenghai and Liu, Tieyan and Ma, Wei-Ying},
  title           = {Dual learning for machine translation},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {820--828},
  keywords        = {nmt},
  timestamp       = {20181201T1030}
}

@Article{he2017-adversarial,
  author          = {He, Warren and Wei, James and Chen, Xinyun and Carlini, Nicholas and Song, Dawn},
  title           = {Adversarial Example Defenses: Ensembles of Weak Defenses Are Not Strong},
  journaltitle    = {arXiv preprint arXiv:1706.04701},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.04701},
  keywords        = {adversarial, ensembles, transferability},
  timestamp       = {20181201T1030}
}

@InCollection{he2017-decoding,
  author          = {He, Di and Lu, Hanqing and Xia, Yingce and Qin, Tao and Wang, Liwei and Liu, Tieyan},
  title           = {Decoding with Value Networks for Neural Machine Translation},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {177--186},
  url             = {http://papers.nips.cc/paper/6622-decoding-with-value-networks-for-neural-machine-translation.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{he2017-deep,
  author          = {He, Luheng and Lee, Kenton and Lewis, Mike and Zettlemoyer, Luke},
  title           = {Deep semantic role labeling: What works and what's next},
  keywords        = {data, srl},
  year            = 2017,
  booktitle       = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  volume          = 1,
  pages           = {473--483},
  timestamp       = {20190107T0951}
}

@Article{he2017-mask,
  author          = {{He}, K. and {Gkioxari}, G. and {Doll{\'a}r}, P. and {Girshick}, R.},
  title           = {{Mask R-CNN}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.06870},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@InProceedings{he2018-decision,
  author          = {Warren He and Bo Li and Dawn Song},
  title           = {Decision Boundary Analysis of Adversarial Examples},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BkpiPMbA-},
  keywords        = {adversarial, theory},
  timestamp       = {20181201T1030}
}

@Article{healy1976-detection,
  author          = {Healy, Alice F},
  title           = {Detection Errors on the Word The: Evidence for Reading Units Larger Than Letters.},
  keywords        = {brain, linguistic},
  journaltitle    = {Journal of Experimental Psychology: Human Perception and Performance},
  year            = 1976,
  volume          = 2,
  number          = 2,
  pages           = 235,
  journal         = {Journal of Experimental Psychology: Human Perception and Performance},
  publisher       = {American Psychological Association},
  timestamp       = {20190106T1045}
}

@Article{heess2017-emergence,
  author          = {Nicolas Heess and Dhruva TB and Srinivasan Sriram and Jay Lemmon and Josh Merel and Greg Wayne and Yuval Tassa and Tom
                  Erez and Ziyu Wang and S. M. Ali Eslami and Martin A. Riedmiller and David Silver},
  title           = {Emergence of Locomotion Behaviours in Rich Environments},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.02286},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InProceedings{heidrich-meisner2007-reinforcement,
  author          = {Heidrich-Meisner, Verena and Lauer, Martin and Igel, Christian and Riedmiller, Martin A},
  title           = {Reinforcement learning in a nutshell.},
  year            = 2007,
  booktitle       = {ESANN},
  organization    = {Citeseer},
  pages           = {277--288},
  timestamp       = {20181201T1030}
}

@InCollection{heikkilae2017-differentially,
  author          = {Heikkil{\"a}, Mikko and Lagerspetz, Eemil and Kaski, Samuel and Shimizu, Kana and Tarkoma, Sasu and Honkela, Antti},
  title           = {Differentially private Bayesian learning on distributed data},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3229--3238},
  url             = {http://papers.nips.cc/paper/6915-differentially-private-bayesian-learning-on-distributed-data.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{hein2017-formal,
  author          = {Hein, Matthias and Andriushchenko, Maksym},
  title           = {Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2263--2273},
  url             = {http://papers.nips.cc/paper/6821-formal-guarantees-on-the-robustness-of-a-classifier-against-adversarial-manipulation.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{heinrich2015-fictitious,
  author          = {Heinrich, Johannes and Lanctot, Marc and Silver, David},
  title           = {Fictitious self-play in extensive-form games},
  year            = 2015,
  booktitle       = {International Conference on Machine Learning},
  pages           = {805--813},
  timestamp       = {20181201T1030}
}

@Article{henaff2016-orthogonal,
  author          = {Mikael Henaff and Arthur Szlam and Yann LeCun},
  title           = {Orthogonal Rnns and Long-Memory Tasks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.06662},
  url             = {http://arxiv.org/abs/1602.06662},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HenaffSL16},
  timestamp       = {20181201T1030}
}

@Article{henaff2017-prediction,
  author          = {{Henaff}, M. and {Zhao}, J. and {LeCun}, Y.},
  title           = {{Prediction Under Uncertainty With Error-Encoding Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.04994},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171104994H},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@InCollection{henao2015-deep,
  author          = {Henao, Ricardo and Gan, Zhe and Lu, James and Carin, Lawrence},
  title           = {Deep Poisson Factor Modeling},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2800--2808},
  url             = {http://papers.nips.cc/paper/5786-deep-poisson-factor-modeling.pdf},
  timestamp       = {20181201T1030}
}

@Article{henderson2017-deep,
  author          = {{Henderson}, P. and {Islam}, R. and {Bachman}, P. and {Pineau}, J. and {Precup}, D. and {Meger}, D.},
  title           = {{Deep Reinforcement Learning That Matters}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = sep,
  eprint          = {1709.06560},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{hendrycks2016-bridging,
  author          = {Dan Hendrycks and Kevin Gimpel},
  title           = {Bridging Nonlinearities and Stochastic Regularizers With Gaussian Error Linear Units},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.08415},
  url             = {http://arxiv.org/abs/1606.08415},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HendrycksG16},
  timestamp       = {20181201T1030}
}

@Article{heng2018-harmonic,
  author          = {{Heng}, W. and {Zhou}, S. and {Jiang}, T.},
  title           = {{Harmonic Adversarial Attack Method}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jul,
  eprint          = {1807.10590},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180710590H},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{henkelman1999-dimer,
  author          = {Henkelman, Graeme and J{\'o}nsson, Hannes},
  title           = {A Dimer Method for Finding Saddle Points on High Dimensional Potential Surfaces Using Only First Derivatives},
  journaltitle    = {The Journal of chemical physics},
  year            = 1999,
  volume          = 111,
  number          = 15,
  pages           = {7010--7022},
  journal         = {The Journal of chemical physics},
  publisher       = {AIP Publishing},
  timestamp       = {20181201T1030}
}

@Article{heo2018-improving,
  author          = {{Heo}, B. and {Lee}, M. and {Yun}, S. and {Choi}, J.~Y.},
  title           = {{Improving Knowledge Distillation With Supporting Adversarial Samples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = may,
  eprint          = {1805.05532},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180505532H},
  archiveprefix   = "arXiv",
  keywords        = {knowledge distillation},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InCollection{hermann2015-teaching,
  author          = {Hermann, Karl Moritz and Kocisky, Tomas and Grefenstette, Edward and Espeholt, Lasse and Kay, Will and Suleyman,
                  Mustafa and Blunsom, Phil},
  title           = {Teaching Machines to Read and Comprehend},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1693--1701},
  url             = {http://papers.nips.cc/paper/5945-teaching-machines-to-read-and-comprehend.pdf},
  timestamp       = {20181201T1030}
}

@Article{hershey2016-cnn,
  author          = {Shawn Hershey and Sourish Chaudhuri and Daniel P. W. Ellis and Jort F. Gemmeke and Aren Jansen and R. Channing Moore
                  and Manoj Plakal and Devin Platt and Rif A. Saurous and Bryan Seybold and Malcolm Slaney and Ron J. Weiss and Kevin
                  W. Wilson},
  title           = {{CNN} Architectures for Large-Scale Audio Classification},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.09430},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{heusel2017-gans,
  author          = {{Heusel}, M. and {Ramsauer}, H. and {Unterthiner}, T. and {Nessler}, B. and {Klambauer}, G. and {Hochreiter}, S.},
  title           = {{GANs Trained By a Two Time-Scale Update Rule Converge To a Nash Equilibrium}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.08500},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {gan, frechet inception distance, fid},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Book{hiai2014-introduction,
  author          = {Hiai, Fumio and Petz, D{\'e}nes},
  title           = {Introduction to matrix analysis and applications},
  year            = 2014,
  publisher       = {Springer Science \& Business Media},
  timestamp       = {20181201T1030}
}

@Article{hill2015-goldilocks,
  author          = {Felix Hill and Antoine Bordes and Sumit Chopra and Jason Weston},
  title           = {The Goldilocks Principle: Reading Children's Books With Explicit Memory Representations},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.02301},
  url             = {http://arxiv.org/abs/1511.02301},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HillBCW15},
  timestamp       = {20181201T1030}
}

@Article{hill2015-learning,
  author          = {Felix Hill and Kyunghyun Cho and Anna Korhonen and Yoshua Bengio},
  title           = {Learning To Understand Phrases By Embedding the Dictionary},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1504.00548},
  url             = {http://arxiv.org/abs/1504.00548},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HillCKB15},
  timestamp       = {20181201T1030}
}

@Article{hill2015-simlex,
  author          = {Hill, Felix and Reichart, Roi and Korhonen, Anna},
  title           = {Simlex-999: Evaluating Semantic Models With (genuine) Similarity Estimation},
  journaltitle    = {Computational Linguistics},
  year            = 2015,
  volume          = 41,
  number          = 4,
  pages           = {665--695},
  journal         = {Computational Linguistics},
  keywords        = {simlex},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{hill2016-learning,
  author          = {Felix Hill and Kyunghyun Cho and Anna Korhonen},
  title           = {Learning Distributed Representations of Sentences From Unlabelled Data},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.03483},
  eprint          = {1602.03483},
  url             = {http://arxiv.org/abs/1602.03483},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/HillCK16},
  timestamp       = {20181201T1030}
}

@InProceedings{hinneburg2000-what,
  author          = {Hinneburg, Alexander and Aggarwal, Charu C. and Keim, Daniel A.},
  title           = {What Is the Nearest Neighbor in High Dimensional Spaces?},
  year            = 2000,
  booktitle       = {Proceedings of the 26th International Conference on Very Large Data Bases},
  series          = {VLDB '00},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  isbn            = {1-55860-715-3},
  pages           = {506--515},
  url             = {http://dl.acm.org/citation.cfm?id=645926.671675},
  acmid           = 671675,
  address         = {San Francisco, CA, USA},
  numpages        = 10,
  timestamp       = {20181201T1030}
}

@InProceedings{hinton1983-optimal,
  author          = {Geoffrey E. Hinton and Terrence J. Sejnowski},
  title           = {Optimal perceptual inference},
  year            = 1983,
  booktitle       = {In CVPR, Washington DC},
  timestamp       = {20181201T1030}
}

@Article{hinton1987-how,
  author          = {Hinton, Geoffrey E and Nowlan, Steven J},
  title           = {How Learning Can Guide Evolution},
  journaltitle    = {Complex systems},
  year            = 1987,
  volume          = 1,
  number          = 3,
  pages           = {495--502},
  journal         = {Complex systems},
  timestamp       = {20181201T1030}
}

@InProceedings{hinton1993-keeping,
  author          = {Hinton, Geoffrey E and Van Camp, Drew},
  title           = {Keeping the neural networks simple by minimizing the description length of the weights},
  year            = 1993,
  booktitle       = {Proceedings of the sixth annual conference on Computational learning theory},
  organization    = {ACM},
  pages           = {5--13},
  keywords        = {variational},
  timestamp       = {20181201T1030}
}

@Article{hinton1995-wake,
  author          = {Hinton, GE and Dayan, P and Frey, BJ and Neal, RM},
  title           = {The "Wake-Sleep" Algorithm for Unsupervised Neural Networks},
  journaltitle    = {Science},
  year            = 1995,
  volume          = 268,
  number          = 5214,
  pages           = {1158--1161},
  issn            = {0036-8075},
  doi             = {10.1126/science.7761831},
  eprint          = {http://science.sciencemag.org/content/268/5214/1158.full.pdf},
  url             = {https://doi.org/10.1126/science.7761831},
  journal         = {Science},
  publisher       = {American Association for the Advancement of Science},
  timestamp       = {20181201T1030}
}

@Article{hinton2002-training,
  author          = {Hinton, Geoffrey E.},
  title           = {Training Products of Experts By Minimizing Contrastive Divergence},
  journaltitle    = {Neural Comput.},
  year            = 2002,
  volume          = 14,
  number          = 8,
  month           = aug,
  pages           = {1771--1800},
  issn            = {0899-7667},
  doi             = {10.1162/089976602760128018},
  url             = {https://doi.org/10.1162/089976602760128018},
  journal         = {Neural Comput.},
  acmid           = 639730,
  address         = {Cambridge, MA, USA},
  issue_date      = {August 2002},
  numpages        = 30,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@InCollection{hinton2003-stochastic,
  author          = {Geoffrey E. Hinton and Sam T. Roweis},
  title           = {Stochastic Neighbor Embedding},
  year            = 2003,
  booktitle       = {Advances in Neural Information Processing Systems 15},
  editor          = {S. Becker and S. Thrun and K. Obermayer},
  publisher       = {MIT Press},
  pages           = {857--864},
  url             = {http://papers.nips.cc/paper/2276-stochastic-neighbor-embedding.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{hinton2005-what,
  author          = {Hinton, Geoffrey E.},
  title           = {What Kind of a Graphical Model is the Brain?},
  year            = 2005,
  booktitle       = {Proceedings of the 19th International Joint Conference on Artificial Intelligence},
  series          = {IJCAI'05},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  location        = {Edinburgh, Scotland},
  pages           = {1765--1775},
  url             = {http://dl.acm.org/citation.cfm?id=1642293.1642643},
  acmid           = 1642643,
  address         = {San Francisco, CA, USA},
  numpages        = 11,
  timestamp       = {20181201T1030}
}

@Article{hinton2006-fast,
  author          = {Hinton, Geoffrey E. and Osindero, Simon and Teh, Yee-Whye},
  title           = {A Fast Learning Algorithm for Deep Belief Nets},
  journaltitle    = {Neural Comput.},
  year            = 2006,
  volume          = 18,
  number          = 7,
  month           = jul,
  pages           = {1527--1554},
  issn            = {0899-7667},
  doi             = {10.1162/neco.2006.18.7.1527},
  url             = {https://doi.org/10.1162/neco.2006.18.7.1527},
  journal         = {Neural Comput.},
  acmid           = 1161605,
  address         = {Cambridge, MA, USA},
  issue_date      = {July 2006},
  numpages        = 28,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{hinton2006-reducing,
  author          = {Hinton, G. E. and Salakhutdinov, R. R.},
  title           = {Reducing the Dimensionality of Data With Neural Networks},
  journaltitle    = {Science},
  year            = 2006,
  volume          = 313,
  number          = 5786,
  pages           = {504-507},
  doi             = {10.1126/science.1127647},
  eprint          = {http://www.sciencemag.org/content/313/5786/504.full.pdf},
  url             = {https://doi.org/10.1126/science.1127647},
  journal         = {Science},
  keywords        = {autoencoder},
  timestamp       = {20181201T1030}
}

@InProceedings{hinton2011-transforming,
  author          = {Hinton, Geoffrey E and Krizhevsky, Alex and Wang, Sida D},
  title           = {Transforming auto-encoders},
  year            = 2011,
  booktitle       = {International Conference on Artificial Neural Networks},
  organization    = {Springer},
  pages           = {44--51},
  keywords        = {capsules},
  timestamp       = {20181201T1030}
}

@Article{hinton2012-improving,
  author          = {Geoffrey E. Hinton and Nitish Srivastava and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
  title           = {Improving Neural Networks By Preventing Co-Adaptation of Feature Detectors},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1207.0580},
  url             = {http://arxiv.org/abs/1207.0580},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1207-0580},
  timestamp       = {20181201T1030}
}

@InCollection{hinton2012-practical,
  author          = {Hinton, GeoffreyE.},
  title           = {A Practical Guide to Training Restricted Boltzmann Machines},
  year            = 2012,
  booktitle       = {Neural Networks: Tricks of the Trade},
  editor          = {Montavon, Gr{\'e}goire and Orr, Genevi{\`e}veB. and M{\"u}ller, Klaus-Robert},
  language        = {English},
  volume          = 7700,
  series          = {Lecture Notes in Computer Science},
  publisher       = {Springer Berlin Heidelberg},
  isbn            = {978-3-642-35288-1},
  pages           = {599-619},
  doi             = {10.1007/978-3-642-35289-8_32},
  url             = {https://doi.org/10.1007/978-3-642-35289-8_32},
  timestamp       = {20181201T1030}
}

@Article{hinton2015-distilling,
  author          = {{Hinton}, G. and {Vinyals}, O. and {Dean}, J.},
  title           = {{Distilling the Knowledge in a Neural Network}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = mar,
  eprint          = {1503.02531},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {distillation, transfer, specialists},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{hinton2018-matrix,
  author          = {J. Hinton},
  title           = {Matrix Capsules With Em Routing},
  journaltitle    = {International Conference on Learning Representations},
  year            = 2018,
  journal         = {International Conference on Learning Representations},
  keywords        = {capsule},
  timestamp       = {20181201T1030}
}

@Article{ho1998-random,
  author          = {Ho, Tin Kam},
  title           = {The Random Subspace Method for Constructing Decision Forests},
  journaltitle    = {IEEE transactions on pattern analysis and machine intelligence},
  year            = 1998,
  volume          = 20,
  number          = 8,
  pages           = {832--844},
  journal         = {IEEE transactions on pattern analysis and machine intelligence},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{ho2016-generative,
  author          = {{Ho}, J. and {Ermon}, S.},
  title           = {{Generative Adversarial Imitation Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.03476},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{hochreiter1995-simplifying,
  author          = {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen and others},
  title           = {Simplifying Neural Nets By Discovering Flat Minima},
  journaltitle    = {Advances in Neural Information Processing Systems},
  year            = 1995,
  pages           = {529--536},
  journal         = {Advances in Neural Information Processing Systems},
  publisher       = {MORGAN KAUFMANN PUBLISHERS},
  timestamp       = {20181201T1030}
}

@Article{hochreiter1997-flat,
  author          = {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  title           = {Flat Minima},
  journaltitle    = {Neural Computation},
  year            = 1997,
  volume          = 9,
  number          = 1,
  pages           = {1--42},
  journal         = {Neural Computation},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{hochreiter1997-long,
  author          = {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  title           = {Long Short-Term Memory},
  journaltitle    = {Neural Comput.},
  year            = 1997,
  volume          = 9,
  number          = 8,
  month           = nov,
  pages           = {1735--1780},
  issn            = {0899-7667},
  doi             = {10.1162/neco.1997.9.8.1735},
  url             = {https://doi.org/10.1162/neco.1997.9.8.1735},
  journal         = {Neural Comput.},
  acmid           = 1246450,
  address         = {Cambridge, MA, USA},
  issue_date      = {November 15, 1997},
  numpages        = 46,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{hochreiter1997-lstm,
  author          = {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  title           = {Lstm Can Solve Hard Long Time Lag Problems},
  journaltitle    = {Advances in neural information processing systems},
  year            = 1997,
  pages           = {473--479},
  journal         = {Advances in neural information processing systems},
  publisher       = {MORGAN KAUFMANN PUBLISHERS},
  timestamp       = {20181201T1030}
}

@Article{hochreiter1998-vanishing,
  author          = {Hochreiter, Sepp},
  title           = {The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions},
  journaltitle    = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
  year            = 1998,
  volume          = 6,
  number          = 02,
  pages           = {107--116},
  journal         = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
  publisher       = {World Scientific},
  timestamp       = {20181201T1030}
}

@Misc{hochreiter2001-gradient,
  author          = {Hochreiter, Sepp and Bengio, Yoshua and Frasconi, Paolo and Schmidhuber, J{\"u}rgen},
  title           = {Gradient flow in recurrent nets: the difficulty of learning long-term dependencies},
  year            = 2001,
  keywords        = {gradient flow, difficulty, rnn, long term dependency},
  publisher       = {A field guide to dynamical recurrent neural networks. IEEE Press},
  timestamp       = {20181201T1030}
}

@InCollection{hofer2017-deep,
  author          = {Hofer, Christoph and Kwitt, Roland and Niethammer, Marc and Uhl, Andreas},
  title           = {Deep Learning with Topological Signatures},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1633--1643},
  url             = {http://papers.nips.cc/paper/6761-deep-learning-with-topological-signatures.pdf},
  timestamp       = {20181201T1030}
}

@Article{hoffer2017-train,
  author          = {{Hoffer}, E. and {Hubara}, I. and {Soudry}, D.},
  title           = {{Train Longer, Generalize Better: Closing the Generalization Gap in Large Batch Training of Neural networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.08741},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv170508741H},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Book{hogben2013-handbook,
  author          = {Hogben, Leslie},
  title           = {Handbook of linear algebra},
  year            = 2013,
  publisher       = {Chapman and Hall/CRC},
  timestamp       = {20181201T1030}
}

@InProceedings{hoiem2012-diagnosing,
  author          = {Hoiem, Derek and Chodpathumwan, Yodsawalai and Dai, Qieyun},
  title           = {Diagnosing error in object detectors},
  year            = 2012,
  booktitle       = {European conference on computer vision},
  organization    = {Springer},
  pages           = {340--353},
  timestamp       = {20181201T1030}
}

@Article{honkela2004-variational,
  author          = {Honkela, Antti and Valpola, Harri},
  title           = {Variational Learning and Bits-Back Coding: an Information-Theoretic View To Bayesian Learning},
  journaltitle    = {IEEE Transactions on Neural Networks},
  year            = 2004,
  volume          = 15,
  number          = 4,
  pages           = {800--810},
  journal         = {IEEE Transactions on Neural Networks},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{hooft1984-quantum,
  author          = {Hooft, Gerard't},
  title           = {Quantum Field Theory for Elementary Particles. Is Quantum Field Theory a Theory?},
  journaltitle    = {Physics Reports},
  year            = 1984,
  volume          = 104,
  number          = {2-4},
  pages           = {129--142},
  journal         = {Physics Reports},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{hopfield1982-neural,
  author          = {Hopfield, J J},
  title           = {Neural Networks and Physical Systems With Emergent Collective Computational Abilities},
  journaltitle    = {Proceedings of the National Academy of Sciences},
  year            = 1982,
  volume          = 79,
  number          = 8,
  pages           = {2554-2558},
  eprint          = {http://www.pnas.org/content/79/8/2554.full.pdf},
  url             = {http://www.pnas.org/content/79/8/2554.abstract},
  journal         = {Proceedings of the National Academy of Sciences},
  timestamp       = {20181201T1030}
}

@Article{hornik1989-multilayer,
  author          = {Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert},
  title           = {Multilayer Feedforward Networks Are Universal Approximators},
  journaltitle    = {Neural networks},
  year            = 1989,
  volume          = 2,
  number          = 5,
  pages           = {359--366},
  journal         = {Neural networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{hosseini2017-deceiving,
  author          = {Hosseini, Hossein and Kannan, Sreeram and Zhang, Baosen and Poovendran, Radha},
  title           = {Deceiving Google's Perspective Api Built for Detecting Toxic Comments},
  journaltitle    = {arXiv preprint arXiv:1702.08138},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.08138},
  timestamp       = {20181201T1030}
}

@Article{hosseini2017-deep,
  author          = {Hossein Hosseini and Radha Poovendran},
  title           = {Deep Neural Networks Do Not Recognize Negative Images},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.06857},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{hou2016-loss,
  author          = {Hou, Lu and Yao, Quanming and Kwok, James T},
  title           = {Loss-Aware Binarization of Deep Networks},
  journaltitle    = {arXiv preprint arXiv:1611.01600},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1611.01600},
  timestamp       = {20181201T1030}
}

@InProceedings{houle2010-can,
  author          = {Houle, Michael E. and Kriegel, Hans-Peter and Kr{\"o}ger, Peer and Schubert, Erich and Zimek, Arthur},
  title           = {Can Shared-neighbor Distances Defeat the Curse of Dimensionality?},
  year            = 2010,
  booktitle       = {Proceedings of the 22Nd International Conference on Scientific and Statistical Database Management},
  series          = {SSDBM'10},
  publisher       = {Springer-Verlag},
  location        = {Heidelberg, Germany},
  isbn            = {3-642-13817-9, 978-3-642-13817-1},
  pages           = {482--500},
  url             = {http://dl.acm.org/citation.cfm?id=1876037.1876078},
  acmid           = 1876078,
  address         = {Berlin, Heidelberg},
  numpages        = 19,
  timestamp       = {20181201T1030}
}

@Article{howard2017-mobilenets,
  author          = {Andrew G. Howard and Menglong Zhu and Bo Chen and Dmitry Kalenichenko and Weijun Wang and Tobias Weyand and Marco
                  Andreetto and Hartwig Adam},
  title           = {Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.04861},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1030}
}

@InProceedings{hu2016-different,
  author          = {Wenpeng Hu and Jiajun Zhang and Nan Zheng},
  title           = {Different Contexts Lead to Different Word Embeddings},
  year            = 2016,
  booktitle       = {COLING},
  timestamp       = {20181201T1030}
}

@Article{hu2016-network,
  author          = {Hengyuan Hu and Rui Peng and Yu{-}Wing Tai and Chi{-}Keung Tang},
  title           = {Network Trimming: {A} Data-Driven Neuron Pruning Approach Towards Efficient Deep Architectures},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1607.03250},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1030}
}

@Article{hu2017-controllable,
  author          = {Zhiting Hu and Zichao Yang and Xiaodan Liang and Ruslan Salakhutdinov and Eric P. Xing},
  title           = {Controllable Text Generation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.00955},
  url             = {http://arxiv.org/abs/1703.00955},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{hu2017-generating,
  author          = {{Hu}, W. and {Tan}, Y.},
  title           = {{Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.05983},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{hu2017-unifying,
  author          = {{Hu}, Z. and {Yang}, Z. and {Salakhutdinov}, R. and {Xing}, E.~P.},
  title           = {{On Unifying Deep Generative Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.00550},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InCollection{huang1992-comparison,
  author          = {Jenq-Neng Huang and Li, Hang and Martin Maechler and R. Douglas Martin and Jim Schimert},
  title           = {A Comparison of Projection Pursuit and Neural Network Regression Modeling},
  year            = 1992,
  booktitle       = {Advances in Neural Information Processing Systems 4},
  editor          = {J.E. Moody and S.J. Hanson and R.P. Lippmann},
  publisher       = {Morgan-Kaufmann},
  pages           = {1159--1166},
  url             = {http://papers.nips.cc/paper/578-a-comparison-of-projection-pursuit-and-neural-network-regression-modeling.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{huang2011-adversarial,
  author          = {Huang, Ling and Joseph, Anthony D and Nelson, Blaine and Rubinstein, Benjamin IP and Tygar, JD},
  title           = {Adversarial machine learning},
  year            = 2011,
  booktitle       = {Proceedings of the 4th ACM workshop on Security and artificial intelligence},
  organization    = {ACM},
  pages           = {43--58},
  keywords        = {adversarial, taxonomy, differential privacy},
  timestamp       = {20181201T1030}
}

@InProceedings{huang2012-improving,
  author          = {Huang, Eric H and Socher, Richard and Manning, Christopher D and Ng, Andrew Y},
  title           = {Improving word representations via global context and multiple word prototypes},
  year            = 2012,
  booktitle       = {Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1},
  organization    = {Association for Computational Linguistics},
  pages           = {873--882},
  keywords        = {scws, polysemy},
  timestamp       = {20181201T1030}
}

@Article{huang2013-entropy,
  author          = {Huang, Haiping and Wong, KY Michael and Kabashima, Yoshiyuki},
  title           = {Entropy Landscape of Solutions in the Binary Perceptron Problem},
  journaltitle    = {Journal of Physics A: Mathematical and Theoretical},
  year            = 2013,
  volume          = 46,
  number          = 37,
  pages           = 375002,
  journal         = {Journal of Physics A: Mathematical and Theoretical},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1030}
}

@InProceedings{huang2014-beyond,
  author          = {Zhen Huang and Jinyu Li and Chao Weng and Chin-Hui Lee},
  title           = {Beyond Cross-entropy: Towards Better Frame-level Objective Functions For Deep Neural Network Training In Automatic
                  Speech Recognition},
  year            = 2014,
  booktitle       = {Interspeech},
  month           = {September},
  url             = {http://research.microsoft.com/apps/pubs/default.aspx?id=230081},
  timestamp       = {20181201T1030}
}

@Article{huang2014-origin,
  author          = {Huang, Haiping and Kabashima, Yoshiyuki},
  title           = {Origin of the Computational Hardness for Learning With Binary Synapses},
  journaltitle    = {Physical Review E},
  year            = 2014,
  volume          = 90,
  number          = 5,
  pages           = 052813,
  journal         = {Physical Review E},
  publisher       = {APS},
  timestamp       = {20181201T1030}
}

@Article{huang2015-learning,
  author          = {Ruitong Huang and Bing Xu and Dale Schuurmans and Csaba Szepesv{\'{a}}ri},
  title           = {Learning With a Strong Adversary},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.03034},
  url             = {http://arxiv.org/abs/1511.03034},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HuangXSS15},
  keywords        = {adversarial, training, min-max},
  timestamp       = {20181201T1030}
}

@Article{huang2015-trends,
  author          = {Huang, Gao and Huang, Guang-Bin and Song, Shiji and You, Keyou},
  title           = {Trends in Extreme Learning Machines: a Review},
  journaltitle    = {Neural Networks},
  year            = 2015,
  volume          = 61,
  pages           = {32--48},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{huang2016-densely,
  author          = {{Huang}, G. and {Liu}, Z. and {Weinberger}, K.~Q.},
  title           = {{Densely Connected Convolutional Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = aug,
  eprint          = {1608.06993},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{huang2016-stacked,
  author          = {Xun Huang and Yixuan Li and Omid Poursaeed and John E. Hopcroft and Serge J. Belongie},
  title           = {Stacked Generative Adversarial Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.04357},
  url             = {http://arxiv.org/abs/1612.04357},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HuangLPHB16},
  timestamp       = {20181201T1030}
}

@InProceedings{huang2016-supervised,
  author          = {Huang, Gao and Guo, Chuan and Kusner, Matt J and Sun, Yu and Sha, Fei and Weinberger, Kilian Q},
  title           = {Supervised Word Mover's Distance},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {4862--4870},
  keywords        = {wmd},
  timestamp       = {20181201T1030}
}

@Article{huang2017-fusionnet,
  author          = {Hsin{-}Yuan Huang and Chenguang Zhu and Yelong Shen and Weizhu Chen},
  title           = {Fusionnet: Fusing Via Fully-Aware Attention With Application To Machine Comprehension},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.07341},
  eprint          = {1711.07341},
  url             = {http://arxiv.org/abs/1711.07341},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1711-07341},
  timestamp       = {20181201T1030}
}

@Article{huang2017-learning,
  author          = {Huang, Furong and Ash, Jordan and Langford, John and Schapire, Robert},
  title           = {Learning Deep Resnet Blocks Sequentially Using Boosting Theory},
  journaltitle    = {arXiv preprint arXiv:1706.04964},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.04964},
  timestamp       = {20181201T1030}
}

@InProceedings{huang2017-speed,
  author          = {Huang, Jonathan and Rathod, Vivek and Sun, Chen and Zhu, Menglong and Korattikara, Anoop and Fathi, Alireza and
                  Fischer, Ian and Wojna, Zbigniew and Song, Yang and Guadarrama, Sergio and others},
  title           = {Speed/accuracy trade-offs for modern convolutional object detectors},
  year            = 2017,
  booktitle       = {IEEE CVPR},
  volume          = 4,
  timestamp       = {20181201T1030}
}

@Article{huang2017-zero,
  author          = {{Huang}, L. and {Ji}, H. and {Cho}, K. and {Voss}, C.~R.},
  title           = {{Zero-Shot Transfer Learning for Event Extraction}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.01066},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {zero shot, event extraction},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@Article{huang2018-multi,
  author          = {{Huang}, L. and {Cho}, K. and {Zhang}, B. and {Ji}, H. and {Knight}, K.},
  title           = {{Multi-Lingual Common Semantic Space Construction Via Cluster-Consistent Word Embedding}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = apr,
  eprint          = {1804.07875},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180407875H},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Artificial Intelligence},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@Article{hubara2016-quantized,
  author          = {Itay Hubara and Matthieu Courbariaux and Daniel Soudry and Ran El{-}Yaniv and Yoshua Bengio},
  title           = {Quantized Neural Networks: Training Neural Networks With Low Precision Weights and Activations},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.07061},
  url             = {http://arxiv.org/abs/1609.07061},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/HubaraCSEB16},
  timestamp       = {20181201T1030}
}

@Article{huesken2003-rcurrent,
  author          = {Michael H{\"u}sken and Peter Stagge},
  title           = {Rcurrent Neural Networks for Time Series Classification},
  journaltitle    = {Neurocomputing},
  year            = 2003,
  volume          = 50,
  pages           = {223 - 235},
  issn            = {0925-2312},
  doi             = {10.1016/S0925-2312(01)00706-8},
  url             = {https://doi.org/10.1016/S0925-2312(01)00706-8},
  journal         = {Neurocomputing},
  keywords        = {Recurrent neural network,Classification,Time,Multitask learning,Generalization},
  timestamp       = {20181201T1030}
}

@Article{huizinga2016-does,
  author          = {Huizinga, Joost and Mouret, Jean-Baptiste and Clune, Jeff},
  title           = {Does Aligning Phenotypic and Genotypic Modularity Improve the Evolution of Neural Networks?},
  journaltitle    = {GECCO},
  year            = 2016,
  journal         = {GECCO},
  timestamp       = {20181201T1030}
}

@InProceedings{hwang2014-fixed,
  author          = {K. Hwang and W. Sung},
  title           = {Fixed-point feedforward deep neural network design using weights -1, 0, and +1},
  year            = 2014,
  booktitle       = {2014 IEEE Workshop on Signal Processing Systems (SiPS)},
  month           = {Oct},
  pages           = {1-6},
  doi             = {10.1109/SiPS.2014.6986082},
  url             = {https://doi.org/10.1109/SiPS.2014.6986082},
  issn            = {2162-3562},
  keywords        = {quantization, ternary},
  timestamp       = {20181201T1030}
}

@InProceedings{iacobacci2015-sensembed,
  author          = {Ignacio Iacobacci and Mohammad Taher Pilehvar and Roberto Navigli},
  title           = {SensEmbed: Learning Sense Embeddings for Word and Relational Similarity},
  year            = 2015,
  booktitle       = {ACL},
  timestamp       = {20181201T1030}
}

@Article{iandola2016-squeezenet,
  author          = {Forrest N. Iandola and Matthew W. Moskewicz and Khalid Ashraf and Song Han and William J. Dally and Kurt Keutzer},
  title           = {Squeezenet: Alexnet-Level Accuracy With 50x Fewer Parameters and {\textless}1MB Model Size},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.07360},
  url             = {http://arxiv.org/abs/1602.07360},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/IandolaMAHDK16},
  keywords        = {compression},
  timestamp       = {20181201T1030}
}

@Misc{igel2000-improving,
  author          = {Christian Igel and Michael H{\"u}sken},
  title           = {Improving the Rprop Learning Algorithm},
  year            = 2000,
  timestamp       = {20181201T1030}
}

@InProceedings{igel2003-neuroevolution,
  author          = {Igel, Christian},
  title           = {Neuroevolution for reinforcement learning using evolution strategies},
  year            = 2003,
  booktitle       = {Evolutionary Computation, 2003. CEC'03. The 2003 Congress on},
  volume          = 4,
  organization    = {IEEE},
  pages           = {2588--2595},
  timestamp       = {20181201T1030}
}

@Article{ioannou2015-training,
  author          = {Yani Ioannou and Duncan P. Robertson and Jamie Shotton and Roberto Cipolla and Antonio Criminisi},
  title           = {Training Cnns With Low-Rank Filters for Efficient Image Classification},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06744},
  journal         = {CoRR},
  keywords        = {pruning, low rank},
  timestamp       = {20181201T1030}
}

@Article{ioffe2015-batch,
  author          = {Sergey Ioffe and Christian Szegedy},
  title           = {Batch Normalization: Accelerating Deep Network Training By Reducing Internal Covariate Shift},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1502.03167},
  url             = {http://arxiv.org/abs/1502.03167},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/IoffeS15},
  keywords        = {bn, batch normalization},
  timestamp       = {20181201T1030}
}

@Article{isola2016-image,
  author          = {Phillip Isola and Jun{-}Yan Zhu and Tinghui Zhou and Alexei A. Efros},
  title           = {Image-To-Image Translation With Conditional Adversarial Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.07004},
  url             = {http://arxiv.org/abs/1611.07004},
  journal         = {CoRR},
  keywords        = {pixel, gan},
  timestamp       = {20181201T1030}
}

@Article{ito2015-prefrontal,
  author          = {Ito, Hiroshi T and Zhang, Sheng-Jia and Witter, Menno P and Moser, Edvard I and Moser, May-Britt},
  title           = {A Prefrontal-Thalamo-Hippocampal Circuit for Goal-Directed Spatialnavigation},
  journaltitle    = {Nature},
  year            = 2015,
  volume          = 522,
  number          = 7554,
  pages           = 50,
  journal         = {Nature},
  publisher       = {Nature Publishing Group},
  timestamp       = {20181201T1030}
}

@Article{iyyer2018-adversarial,
  author          = {Mohit Iyyer and John Wieting and Kevin Gimpel and Luke Zettlemoyer},
  title           = {Adversarial Example Generation With Syntactically Controlled Paraphrase Networks},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1804.06059},
  eprint          = {1804.06059},
  url             = {http://arxiv.org/abs/1804.06059},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1804-06059},
  keywords        = {adversarial, attack, text, paraphrase, scpn},
  timestamp       = {20181201T1030}
}

@Article{izhikevich2003-simple,
  author          = {E. M. Izhikevich},
  title           = {Simple Model of Spiking Neurons},
  journaltitle    = {IEEE Transactions on Neural Networks},
  year            = 2003,
  volume          = 14,
  number          = 6,
  month           = {Nov},
  pages           = {1569-1572},
  issn            = {1045-9227},
  doi             = {10.1109/TNN.2003.820440},
  url             = {https://doi.org/10.1109/TNN.2003.820440},
  journal         = {IEEE Transactions on Neural Networks},
  timestamp       = {20181201T1030}
}

@InProceedings{jacob1993-evolution,
  author          = {Jacob, Christian and Rehder, Jan},
  title           = {Evolution of neural net architectures by a hierarchical grammar-based genetic system},
  year            = 1993,
  booktitle       = {Artificial Neural Nets and Genetic Algorithms},
  organization    = {Springer},
  pages           = {72--79},
  timestamp       = {20181201T1030}
}

@Article{jacobs1991-adaptive,
  author          = {Jacobs, Robert A. and Jordan, Michael I. and Nowlan, Steven J. and Hinton, Geoffrey E.},
  title           = {Adaptive Mixtures of Local Experts},
  journaltitle    = {Neural Comput.},
  year            = 1991,
  volume          = 3,
  number          = 1,
  month           = mar,
  pages           = {79--87},
  issn            = {0899-7667},
  doi             = {10.1162/neco.1991.3.1.79},
  url             = {https://doi.org/10.1162/neco.1991.3.1.79},
  journal         = {Neural Comput.},
  acmid           = 1351018,
  address         = {Cambridge, MA, USA},
  issue_date      = {Spring 1991},
  numpages        = 9,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@InProceedings{jacobsen2018-revnet,
  author          = {J{\"o}rn-Henrik Jacobsen and Arnold W.M. Smeulders and Edouard Oyallon},
  title           = {i-RevNet: Deep Invertible Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HJsjkMb0Z},
  timestamp       = {20181201T1030}
}

@Article{jaderberg2014-speeding,
  author          = {Jaderberg, Max and Vedaldi, Andrea and Zisserman, Andrew},
  title           = {Speeding Up Convolutional Neural Networks With Low Rank Expansions},
  journaltitle    = {arXiv preprint arXiv:1405.3866},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1405.3866},
  keywords        = {compression, low rank},
  timestamp       = {20181201T1030}
}

@InCollection{jaderberg2015-spatial,
  author          = {Jaderberg, Max and Simonyan, Karen and Zisserman, Andrew and kavukcuoglu, koray},
  title           = {Spatial Transformer Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2017--2025},
  url             = {http://papers.nips.cc/paper/5854-spatial-transformer-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{jaderberg2016-decoupled,
  author          = {{Jaderberg}, M. and {Czarnecki}, W.~M. and {Osindero}, S. and {Vinyals}, O. and {Graves}, A. and {Kavukcuoglu}, K.},
  title           = {{Decoupled Neural Interfaces Using Synthetic Gradients}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = aug,
  eprint          = {1608.05343},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {parallel, sgd, backprop},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{jaeger2001-echo,
  author          = {Jaeger, Herbert},
  title           = {The "Echo State" Approach To Analysing and Training Recurrent Neural Networks-With an Erratum Note},
  journaltitle    = {Bonn, Germany: German National Research Center for Information Technology GMD Technical Report},
  year            = 2001,
  volume          = 148,
  number          = 34,
  pages           = 13,
  journal         = {Bonn, Germany: German National Research Center for Information Technology GMD Technical Report},
  keywords        = {echo state network},
  timestamp       = {20181201T1030}
}

@Article{jaeger2004-harnessing,
  author          = {Jaeger, Herbert and Haas, Harald},
  title           = {Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication},
  journaltitle    = {science},
  year            = 2004,
  volume          = 304,
  number          = 5667,
  pages           = {78--80},
  journal         = {science},
  keywords        = {chaos, reservoir},
  publisher       = {American Association for the Advancement of Science},
  timestamp       = {20181201T1030}
}

@Article{jaeger2007-echo,
  author          = {Jaeger, H.},
  title           = {{E}cho State Network},
  journaltitle    = Scholarpedia,
  year            = 2007,
  volume          = 2,
  number          = 9,
  pages           = 2330,
  note            = {{revision #151757}},
  journal         = Scholarpedia,
  timestamp       = {20181201T1030}
}

@Book{james2013-introduction,
  author          = {James, Gareth and Witten, Daniela and Hastie, Trevor and Tibshirani, Robert},
  title           = {An Introduction to Statistical Learning},
  year            = 2013,
  volume          = 112,
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{jang2016-categorical,
  author          = {{Jang}, E. and {Gu}, S. and {Poole}, B.},
  title           = {{Categorical Reparameterization With Gumbel-Softmax}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = nov,
  eprint          = {1611.01144},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {gumbel,dicrete},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{jani2015-introduction,
  author          = {{Jani{\v s}}, V.},
  title           = {{Introduction To Mean-Field Theory of Spin Glass Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = jun,
  eprint          = {1506.07128},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Condensed Matter - Disordered Systems and Neural Networks},
  primaryclass    = "cond-mat.dis-nn",
  timestamp       = {20181201T1030}
}

@InProceedings{jankovic2009-new,
  author          = {Jankovic, Marko V. and Rubens, Neil},
  title           = {A New Probabilistic Approach to On-line Learning in Artificial Neural Networks},
  year            = 2009,
  booktitle       = {Proceedings of the 3rd International Conference on Applied Mathematics, Simulation, Modelling, Circuits, Systems and
                  Signals},
  series          = {ASMCSS'09},
  publisher       = {World Scientific and Engineering Academy and Society (WSEAS)},
  location        = {Vouliagmeni, Athens, Greece},
  isbn            = {978-960-474-147-2},
  pages           = {226--231},
  url             = {http://dl.acm.org/citation.cfm?id=1737863.1737904},
  acmid           = 1737904,
  address         = {Stevens Point, Wisconsin, USA},
  keywords        = {Hebbian learning rule, born rule, probabilistic PSA/PCA, von Neumann entropy},
  numpages        = 6,
  timestamp       = {20181201T1030}
}

@Article{jankovic2010-probabilistic,
  author          = {Marko V. Jankovic},
  title           = {Probabilistic Approach To Neural Networks Computation Based on Quantum Probability Model Probabilistic Principal
                  Subspace Analysis Example},
  journaltitle    = {CoRR},
  year            = 2010,
  volume          = {abs/1001.4301},
  url             = {http://arxiv.org/abs/1001.4301},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1001-4301},
  timestamp       = {20181201T1030}
}

@InProceedings{jarrett2009-what,
  author          = {Jarrett, Kevin and Kavukcuoglu, Koray and LeCun, Yann and others},
  title           = {What is the best multi-stage architecture for object recognition?},
  year            = 2009,
  booktitle       = {Computer Vision, 2009 IEEE 12th International Conference on},
  organization    = {IEEE},
  pages           = {2146--2153},
  keywords        = {random},
  timestamp       = {20181201T1030}
}

@Article{jastrz2017-three,
  author          = {{Jastrz{\c e}bski}, S. and {Kenton}, Z. and {Arpit}, D. and {Ballas}, N. and {Fischer}, A. and {Bengio}, Y. and
                  {Storkey}, A.},
  title           = {{Three Factors Influencing Minima in SGD}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.04623},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171104623J},
  archiveprefix   = "arXiv",
  keywords        = {generalization, sgd, minima, batch size, learning rate, equilibrium distribution, memorization},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{jastrz2018-dnns,
  author          = {{Jastrz{\c e}bski}, S. and {Kenton}, Z. and {Ballas}, N. and {Fischer}, A. and {Bengio}, Y. and {Storkey}, A.},
  title           = {{DNN's Sharpest Directions Along the Sgd Trajectory}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jul,
  eprint          = {1807.05031},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180705031J},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Machine Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{jastrzebski2018-residual,
  author          = {Stanisław Jastrzebski and Devansh Arpit and Nicolas Ballas and Vikas Verma and Tong Che and Yoshua Bengio},
  title           = {Residual Connections Encourage Iterative Inference},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SJa9iHgAZ},
  timestamp       = {20181201T1030}
}

@Article{jastrzkebski2018-finding,
  author          = {Jastrz{k{e}}bski, Stanis{\l}aw and Kenton, Zachary and Arpit, Devansh and Ballas, Nicolas and Fischer, Asja and Bengio,
                  Yoshua and Storkey, Amos},
  title           = {Finding Flatter Minima With Sgd},
  journaltitle    = {ICLR Workshop},
  year            = 2018,
  journal         = {ICLR Workshop},
  timestamp       = {20181201T1030}
}

@Article{jastrzkebski2018-sgd,
  author          = {Jastrz{k{e}}bski, Stanis{\l}aw and Kenton, Zac and Ballas, Nicolas and Fischer, Asja and Storkey, Amos and Bengio,
                  Yoshua},
  title           = {Sgd Smooths the Sharpest Directions},
  journaltitle    = {ICLR Review},
  year            = 2018,
  journal         = {ICLR Review},
  keywords        = {sgd},
  timestamp       = {20181201T1030}
}

@Article{jean2014-using,
  author          = {S{\'{e}}bastien Jean and Kyunghyun Cho and Roland Memisevic and Yoshua Bengio},
  title           = {On Using Very Large Target Vocabulary for Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.2007},
  url             = {http://arxiv.org/abs/1412.2007},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/JeanCMB14},
  timestamp       = {20181201T1030}
}

@Article{jegou2016-one,
  author          = {J{\'e}gou, Simon and Drozdzal, Michal and Vazquez, David and Romero, Adriana and Bengio, Yoshua},
  title           = {The One Hundred Layers Tiramisu: Fully Convolutional Densenets for Semantic Segmentation},
  journaltitle    = {arXiv preprint arXiv:1611.09326},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1611.09326},
  timestamp       = {20181201T1030}
}

@Article{ji1990-generalizing,
  author          = {Ji, Chuanyi and Snapp, Robert R and Psaltis, Demetri},
  title           = {Generalizing Smoothness Constraints From Discrete Samples},
  journaltitle    = {Neural Computation},
  year            = 1990,
  volume          = 2,
  number          = 2,
  pages           = {188--197},
  journal         = {Neural Computation},
  keywords        = {pruning, saliency},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@InCollection{ji2017-deep,
  author          = {Ji, Pan and Zhang, Tong and Li, Hongdong and Salzmann, Mathieu and Reid, Ian},
  title           = {Deep Subspace Clustering Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {23--32},
  url             = {http://papers.nips.cc/paper/6608-deep-subspace-clustering-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{jia2016-data,
  author          = {Robin Jia and Percy Liang},
  title           = {Data Recombination for Neural Semantic Parsing},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.03622},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{jia2017-adversarial,
  author          = {Jia, Robin and Liang, Percy},
  title           = {Adversarial Examples for Evaluating Reading Comprehension Systems},
  journaltitle    = {arXiv preprint arXiv:1707.07328},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.07328},
  keywords        = {adversarial, text, reading comprehension},
  timestamp       = {20181201T1030}
}

@Thesis{jiang2018-brainnet,
  author          = {Jiang, Linxing and Losey, Darby and Stocco, Andrea and Abernethy, Justin and Prat, Chantel and Rao, Rajesh},
  title           = {BrainNet: First Multi-person Direct Brain-to-Brain Communication Model},
  type            = {phd},
  institution     = {University of Washington},
  year            = 2018,
  keywords        = {brainnet, bbi},
  timestamp       = {20181201T1030}
}

@Article{jin2009-impossibility,
  author          = {Jin, Jiashun},
  title           = {Impossibility of Successful Classification When Useful Features Are Rare and Weak},
  journaltitle    = {Proceedings of the National Academy of Sciences},
  year            = 2009,
  volume          = 106,
  number          = 22,
  pages           = {8859-8864},
  doi             = {10.1073/pnas.0903931106},
  eprint          = {http://www.pnas.org/content/106/22/8859.full.pdf},
  url             = {https://doi.org/10.1073/pnas.0903931106},
  journal         = {Proceedings of the National Academy of Sciences},
  timestamp       = {20181201T1030}
}

@Article{jin2017-accelerated,
  author          = {{Jin}, C. and {Netrapalli}, P. and {Jordan}, M.~I.},
  title           = {{Accelerated Gradient Descent Escapes Saddle Points Faster Than Gradient Descent}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.10456},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171110456J},
  archiveprefix   = "arXiv",
  keywords        = {sgd},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{jin2017-how,
  author          = {Chi Jin and Rong Ge and Praneeth Netrapalli and Sham M. Kakade and Michael I. Jordan},
  title           = {How To Escape Saddle Points Efficiently},
  keywords        = {pgd, saddle points},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.00887},
  eprint          = {1703.00887},
  url             = {http://arxiv.org/abs/1703.00887},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/Jin0NKJ17},
  timestamp       = {20190110T1318}
}

@Article{jin2017-introspective,
  author          = {Long Jin and Justin Lazarow and Zhuowen Tu},
  title           = {Introspective Classifier Learning: Empower Generatively},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.07816},
  url             = {http://arxiv.org/abs/1704.07816},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/JinLT17},
  timestamp       = {20181201T1030}
}

@Article{jing2017-gated,
  author          = {Jing, Li and Gulcehre, Caglar and Peurifoy, John and Shen, Yichen and Tegmark, Max and Solja{\v{c}}i{\'c}, Marin and
                  Bengio, Yoshua},
  title           = {Gated Orthogonal Recurrent Units: on Learning To Forget},
  journaltitle    = {arXiv preprint arXiv:1706.02761},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.02761},
  timestamp       = {20181201T1030}
}

@Article{jo2017-measuring,
  author          = {{Jo}, J. and {Bengio}, Y.},
  title           = {{Measuring the Tendency of Cnns To Learn Surface Statistical Regularities}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.11561},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171111561J},
  archiveprefix   = "arXiv",
  keywords        = {cnn, adversarial, theory, fft},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{johnson2016-googles,
  author          = {Melvin Johnson and Mike Schuster and Quoc V. Le and Maxim Krikun and Yonghui Wu and Zhifeng Chen and Nikhil Thorat and
                  Fernanda B. Vi{\'{e}}gas and Martin Wattenberg and Greg Corrado and Macduff Hughes and Jeffrey Dean},
  title           = {Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.04558},
  url             = {http://arxiv.org/abs/1611.04558},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/JohnsonSLKWCTVW16},
  timestamp       = {20181201T1030}
}

@InProceedings{johnson2016-perceptual,
  author          = {Johnson, Justin and Alahi, Alexandre and Fei-Fei, Li},
  title           = {Perceptual losses for real-time style transfer and super-resolution},
  year            = 2016,
  booktitle       = {European Conference on Computer Vision},
  organization    = {Springer},
  pages           = {694--711},
  keywords        = {style transfer},
  timestamp       = {20181201T1030}
}

@Article{johnson2017-inferring,
  author          = {{Johnson}, J. and {Hariharan}, B. and {van der Maaten}, L. and {Hoffman}, J. and {Fei-Fei}, L. and {Zitnick}, C.~L. and
                  {Girshick}, R.},
  title           = {{Inferring and Executing Programs for Visual Reasoning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.03633},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {differentiable programming},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{jolicoeur1985-time,
  author          = {Jolicoeur, Pierre},
  title           = {The Time To Name Disoriented Natural Objects},
  keywords        = {mental rotation},
  journaltitle    = {Memory \& Cognition},
  year            = 1985,
  volume          = 13,
  number          = 4,
  pages           = {289--303},
  journal         = {Memory \& Cognition},
  publisher       = {Springer},
  timestamp       = {20181228T1051}
}

@InProceedings{jorge-botana2011,
  author          = {Guillermo Jorge-Botana and Jos{\'e} Antonio Le{\'o}n and Ricardo Olmos},
  title           = {The representation of polysemy through vectors : some building blocks for constructing models and applications with
                  LSA},
  year            = 2011,
  booktitle       = {Int. J. Cont. Engineering Education and Life-Long Learning},
  timestamp       = {20181201T1030}
}

@InCollection{joshi2017-aggressive,
  author          = {Joshi, Bikash and Amini, Massih-Reza and Partalas, Ioannis and Iutzeler, Franck and Maximov, Yury},
  title           = {Aggressive Sampling for Multi-class to Binary Reduction with Applications to Text Classification},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4162--4171},
  url             = {http://papers.nips.cc/paper/7004-aggressive-sampling-for-multi-class-to-binary-reduction-with-applications-to-text-classification.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{joulin2015-inferring,
  author          = {Joulin, Armand and Mikolov, Tomas},
  title           = {Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {190--198},
  url             = {http://papers.nips.cc/paper/5857-inferring-algorithmic-patterns-with-stack-augmented-recurrent-nets.pdf},
  timestamp       = {20181201T1030}
}

@Article{joulin2016-bag,
  author          = {{Joulin}, A. and {Grave}, E. and {Bojanowski}, P. and {Mikolov}, T.},
  title           = {{Bag of Tricks for Efficient Text Classification}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jul,
  eprint          = {1607.01759},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@Article{joulin2016-fasttext,
  author          = {Armand Joulin and Edouard Grave and Piotr Bojanowski and Matthijs Douze and Herv{\'{e}} J{\'{e}}gou and Tomas Mikolov},
  title           = {Fasttext.zip: Compressing Text Classification Models},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.03651},
  url             = {http://arxiv.org/abs/1612.03651},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/JoulinGBDJM16},
  keywords        = {quantization, product quantization, retraining, nlp, text classification},
  timestamp       = {20181201T1030}
}

@InProceedings{jozefowicz2015,
  author          = {Jozefowicz, Rafal and Zaremba, Wojciech and Sutskever, Ilya},
  title           = {An empirical exploration of recurrent network architectures},
  year            = 2015,
  booktitle       = {Proceedings of the 32nd International Conference on Machine Learning (ICML-15)},
  pages           = {2342--2350},
  timestamp       = {20181201T1030}
}

@Article{jozefowicz2016-exploring,
  author          = {Jozefowicz, Rafal and Vinyals, Oriol and Schuster, Mike and Shazeer, Noam and Wu, Yonghui},
  title           = {Exploring the Limits of Language Modeling},
  journaltitle    = {arXiv preprint arXiv:1602.02410},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1602.02410},
  timestamp       = {20181201T1030}
}

@InCollection{jun2015-human,
  author          = {Jun, Kwang-Sung and Zhu, Xiaojin and Rogers, Timothy T and Yang, Zhuoran and yuan, ming},
  title           = {Human Memory Search as Initial-Visit Emitting Random Walk},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1072--1080},
  url             = {http://papers.nips.cc/paper/5878-human-memory-search-as-initial-visit-emitting-random-walk.pdf},
  timestamp       = {20181201T1030}
}

@Article{junczys-dowmunt2016-is,
  author          = {{Junczys-Dowmunt}, M. and {Dwojak}, T. and {Hoang}, H.},
  title           = {{Is Neural Machine Translation Ready for Deployment? a Case Study on 30 Translation Directions}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = oct,
  eprint          = {1610.01108},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{kaiser2016-can,
  author          = {Kaiser, {\L}ukasz and Bengio, Samy},
  title           = {Can Active Memory Replace Attention?},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {3781--3789},
  timestamp       = {20181201T1030}
}

@Article{kaiser2017-one,
  author          = {{Kaiser}, L. and {Gomez}, A.~N. and {Shazeer}, N. and {Vaswani}, A. and {Parmar}, N. and {Jones}, L. and {Uszkoreit},
                  J.},
  title           = {{One Model To Learn Them All}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.05137},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {multi-task},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InProceedings{kakade2002-natural,
  author          = {Kakade, Sham M},
  title           = {A Natural Policy Gradient},
  year            = 2002,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1531--1538},
  timestamp       = {20181201T1030}
}

@InProceedings{kalchbrenner2013-recurrent,
  author          = {Kalchbrenner, Nal and Blunsom, Phil},
  title           = {Recurrent Continuous Translation Models.},
  year            = 2013,
  booktitle       = {EMNLP},
  volume          = 3,
  number          = 39,
  pages           = 413,
  timestamp       = {20181201T1030}
}

@Article{kalchbrenner2016-neural,
  author          = {Kalchbrenner, Nal and Espeholt, Lasse and Simonyan, Karen and Oord, Aaron van den and Graves, Alex and Kavukcuoglu,
                  Koray},
  title           = {Neural Machine Translation in Linear Time},
  journaltitle    = {arXiv preprint arXiv:1610.10099},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1610.10099},
  keywords        = {bytenet, cnn, nlp, translation},
  timestamp       = {20181201T1030}
}

@Article{karaletsos2015-automatic,
  author          = {{Karaletsos}, T. and {R{\"a}tsch}, G.},
  title           = {{Automatic Relevance Determination for Deep Generative Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = may,
  eprint          = {1505.07765},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2015arXiv150507765K},
  archiveprefix   = "arXiv",
  keywords        = {pruning, bayesian},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{karaletsos2015-bayesian,
  author          = {Karaletsos, Theofanis and Belongie, Serge and R{\"a}tsch, Gunnar},
  title           = {Bayesian Representation Learning With Oracle Constraints},
  journaltitle    = {arXiv preprint arXiv:1506.05011},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1506.05011},
  timestamp       = {20181201T1030}
}

@Article{karolina2017-computing,
  author          = {{Karolina Dziugaite}, Gintare and {Roy}, Daniel M.},
  title           = {{Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks With Many More Parameters Than
                  Training Data}},
  journaltitle    = {arXiv e-prints},
  year            = 2017,
  eid             = {arXiv:1703.11008},
  month           = Mar,
  pages           = {arXiv:1703.11008},
  eprint          = {1703.11008},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/\#abs/2017arXiv170311008K},
  archiveprefix   = {arXiv},
  keywords        = {Computer Science - Machine Learning},
  primaryclass    = {cs.LG},
  timestamp       = {20190113T0944}
}

@Article{karpathy2015-visualizing,
  author          = {Andrej Karpathy and Justin Johnson and Fei{-}Fei Li},
  title           = {Visualizing and Understanding Recurrent Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.02078},
  url             = {http://arxiv.org/abs/1506.02078},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/KarpathyJL15},
  keywords        = {interpret},
  timestamp       = {20181201T1030}
}

@Article{karras2018-style,
  author          = {{Karras}, Tero and {Laine}, Samuli and {Aila}, Timo},
  title           = {{A Style-Based Generator Architecture for Generative Adversarial Networks}},
  journaltitle    = {arXiv e-prints},
  year            = 2018,
  eid             = {arXiv:1812.04948},
  month           = Dec,
  pages           = {arXiv:1812.04948},
  eprint          = {1812.04948},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/\#abs/2018arXiv181204948K},
  archiveprefix   = {arXiv},
  keywords        = {gan, style, perceptual path length},
  primaryclass    = {cs.NE},
  timestamp       = {20181215T1720}
}

@Article{kaslik2012-nonlinear,
  author          = {Kaslik, Eva and Sivasundaram, Seenith},
  title           = {Nonlinear Dynamics and Chaos in Fractional-Order Neural Networks},
  journaltitle    = {Neural Networks},
  year            = 2012,
  volume          = 32,
  pages           = {245--256},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@InProceedings{kato2018-neural,
  author          = {Kato, Hiroharu and Ushiku, Yoshitaka and Harada, Tatsuya},
  title           = {Neural 3D Mesh Renderer},
  year            = 2018,
  booktitle       = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  timestamp       = {20181201T1030}
}

@InProceedings{kawaguchi2016-deep,
  author          = {Kawaguchi, Kenji},
  title           = {Deep learning without poor local minima},
  year            = 2016,
  booktitle       = {Advances In Neural Information Processing Systems},
  pages           = {586--594},
  timestamp       = {20181201T1030}
}

@Article{kawaguchi2017-generalization,
  author          = {Kawaguchi, Kenji and Kaelbling, Leslie Pack and Bengio, Yoshua},
  title           = {Generalization in Deep Learning},
  journaltitle    = {arXiv preprint arXiv:1710.05468},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1710.05468},
  timestamp       = {20181201T1030}
}

@Article{kawaguchi2018-generalization,
  author          = {{Kawaguchi}, K. and {Bengio}, Y.},
  title           = {{Generalization in Machine Learning Via Analytical Learning Theory}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.07426},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180207426K},
  archiveprefix   = "arXiv",
  keywords        = {generalization, analytical learning theory, measure theory},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{kearns1994-learnability,
  author          = {Kearns, Michael and Mansour, Yishay and Ron, Dana and Rubinfeld, Ronitt and Schapire, Robert E. and Sellie, Linda},
  title           = {On the Learnability of Discrete Distributions},
  year            = 1994,
  booktitle       = {Proceedings of the Twenty-sixth Annual ACM Symposium on Theory of Computing},
  series          = {STOC '94},
  publisher       = {ACM},
  location        = {Montreal, Quebec, Canada},
  isbn            = {0-89791-663-8},
  pages           = {273--282},
  doi             = {10.1145/195058.195155},
  url             = {https://doi.org/10.1145/195058.195155},
  acmid           = 195155,
  address         = {New York, NY, USA},
  numpages        = 10,
  timestamp       = {20181201T1030}
}

@Article{kehagias1997-predictive,
  author          = {Ath. Kehagias and Vas. Petridis},
  title           = {Predictive Modular Neural Networks for Time Series Classification},
  journaltitle    = {Neural Networks},
  year            = 1997,
  volume          = 10,
  number          = 1,
  pages           = {31 - 49},
  issn            = {0893-6080},
  doi             = {10.1016/S0893-6080(96)00040-8},
  url             = {https://doi.org/10.1016/S0893-6080(96)00040-8},
  journal         = {Neural Networks},
  keywords        = {Modular neural networks,Hierarchical neural networks,Adaptive neural networks,Time
                  series,Classification,Prediction,Bayesian decision rules},
  timestamp       = {20181201T1030}
}

@InProceedings{keke2312018-pawe,
  author          = {Taygun Keke231 and Laurens J P Krijthe Van Der Maaten and David M. J. Tax},
  title           = {PAWE: Polysemy Aware Word Embeddings},
  year            = 2018,
  booktitle       = {ICISDM '18},
  timestamp       = {20181201T1030}
}

@Article{kendall2015-bayesian,
  author          = {Alex Kendall and Vijay Badrinarayanan and Roberto Cipolla},
  title           = {Bayesian Segnet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.02680},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{kendall2017-multi,
  author          = {Alex Kendall and Yarin Gal and Roberto Cipolla},
  title           = {Multi-Task Learning Using Uncertainty To Weigh Losses for Scene Geometry and Semantics},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1705.07115},
  journal         = {CoRR},
  keywords        = {bayesian, bn},
  timestamp       = {20181201T1030}
}

@Article{kendall2017-what,
  author          = {Alex Kendall and Yarin Gal},
  title           = {What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.04977},
  journal         = {CoRR},
  keywords        = {bayesian, bn},
  timestamp       = {20181201T1030}
}

@InCollection{kennedy2011-particle,
  author          = {Kennedy, James},
  title           = {Particle Swarm Optimization},
  year            = 2011,
  booktitle       = {Encyclopedia of machine learning},
  publisher       = {Springer},
  pages           = {760--766},
  keywords        = {pso},
  timestamp       = {20181201T1030}
}

@Article{keskar2016-large,
  author          = {Nitish Shirish Keskar and Dheevatsa Mudigere and Jorge Nocedal and Mikhail Smelyanskiy and Ping Tak Peter Tang},
  title           = {On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.04836},
  url             = {http://arxiv.org/abs/1609.04836},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/KeskarMNST16},
  timestamp       = {20181201T1030}
}

@Article{khaligh-razavi2014-deep,
  author          = {Khaligh-Razavi, Seyed-Mahdi and Kriegeskorte, Nikolaus},
  title           = {Deep Supervised, But Not Unsupervised, Models May Explain It Cortical Representation},
  journaltitle    = {PLoS computational biology},
  year            = 2014,
  volume          = 10,
  number          = 11,
  pages           = {e1003915},
  journal         = {PLoS computational biology},
  publisher       = {Public Library of Science},
  timestamp       = {20181201T1030}
}

@InProceedings{khrulkov2018-expressive,
  author          = {Valentin Khrulkov and Alexander Novikov and Ivan Oseledets},
  title           = {Expressive Power of Recurrent Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=S1WRibb0Z},
  timestamp       = {20181201T1030}
}

@Article{kiela2018-dynamic,
  author          = {{Kiela}, D. and {Wang}, C. and {Cho}, K.},
  title           = {Dynamic Meta-Embeddings for Improved Sentence Representations},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = apr,
  eprint          = {1804.07983},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180407983K},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@Article{kim2010-tree,
  author          = {Kim, Seyoung and Xing, Eric P},
  title           = {Tree-Guided Group Lasso for Multi-Task Regression With Structured Sparsity},
  journaltitle    = {Proceedings of the 27th International Conference on Machine Learning},
  year            = 2010,
  journal         = {Proceedings of the 27th International Conference on Machine Learning},
  timestamp       = {20181201T1030}
}

@Book{kim2012-japanese,
  author          = {Tae Kim},
  title           = {Japanese Grammar Guide},
  year            = 2012,
  url             = {http://www.guidetojapanese.org/learn/grammar},
  month           = Nov,
  timestamp       = {20190117T1726}
}

@Article{kim2014-convolutional,
  author          = {Yoon Kim},
  title           = {Convolutional Neural Networks for Sentence Classification},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1408.5882},
  journal         = {CoRR},
  keywords        = {wordcnn},
  timestamp       = {20181201T1030}
}

@InProceedings{kim2014-x1000,
  author          = {Kim, Jonghong and Hwang, Kyuyeon and Sung, Wonyong},
  title           = {X1000 real-time phoneme recognition VLSI using feed-forward deep neural networks},
  year            = 2014,
  booktitle       = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  organization    = {IEEE},
  pages           = {7510--7514},
  timestamp       = {20181201T1030}
}

@Article{kim2015-bayesian,
  author          = {{Kim}, B. and {Rudin}, C. and {Shah}, J.},
  title           = {{The Bayesian Case Model: a Generative Approach for Case-Based Reasoning and Prototype Classification}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = mar,
  eprint          = {1503.01161},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{kim2015-character,
  author          = {Kim, Yoon and Jernite, Yacine and Sontag, David and Rush, Alexander M},
  title           = {Character-Aware Neural Language Models},
  journaltitle    = {arXiv preprint arXiv:1508.06615},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1508.06615},
  keywords        = {charlstm},
  timestamp       = {20181201T1030}
}

@InCollection{kim2015-mind,
  author          = {Kim, Been and Shah, Julie A and Doshi-Velez, Finale},
  title           = {Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2260--2268},
  url             = {http://papers.nips.cc/paper/5957-mind-the-gap-a-generative-approach-to-interpretable-feature-selection-and-extraction.pdf},
  timestamp       = {20181201T1030}
}

@Article{kim2016-bitwise,
  author          = {Kim, Minje and Smaragdis, Paris},
  title           = {Bitwise Neural Networks},
  journaltitle    = {arXiv preprint arXiv:1601.06071},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1601.06071},
  keywords        = {quantization, binary, xnor},
  timestamp       = {20181201T1030}
}

@Article{kim2016-sequence,
  author          = {Yoon Kim and Alexander M. Rush},
  title           = {Sequence-Level Knowledge Distillation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.07947},
  url             = {http://arxiv.org/abs/1606.07947},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/KimR16a},
  timestamp       = {20181201T1030}
}

@Article{kim2017-adversarially,
  author          = {Kim, Yoon and Zhang, Kelly and Rush, Alexander M and LeCun, Yann and others},
  title           = {Adversarially Regularized Autoencoders for Generating Discrete Structures},
  journaltitle    = {arXiv preprint arXiv:1706.04223},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.04223},
  timestamp       = {20181201T1030}
}

@Article{kim2017-structured,
  author          = {Kim, Yoon and Denton, Carl and Hoang, Luong and Rush, Alexander M},
  title           = {Structured Attention Networks},
  journaltitle    = {arXiv preprint arXiv:1702.00887},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.00887},
  keywords        = {attention, self attention},
  timestamp       = {20181201T1030}
}

@InProceedings{kindermans2018-learning,
  author          = {Pieter-Jan Kindermans and Kristof T. Sch{\"u}tt and Maximilian Alber and Klaus-Robert M{\"u}ller and Dumitru Erhan and
                  Been Kim and Sven D{\"a}hne},
  title           = {Learning how to explain neural networks: PatternNet and PatternAttribution},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=Hkn7CBaTW},
  timestamp       = {20181201T1030}
}

@Article{kingma2013-auto,
  author          = {{Kingma}, D.~P and {Welling}, M.},
  title           = {{Auto-Encoding Variational Bayes}},
  journaltitle    = {ArXiv e-prints},
  year            = 2013,
  month           = dec,
  eprint          = {1312.6114},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {vae, re-parameterization},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{kingma2014-adam,
  author          = {Diederik P. Kingma and Jimmy Ba},
  title           = {Adam: {A} Method for Stochastic Optimization},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6980},
  url             = {http://arxiv.org/abs/1412.6980},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/KingmaB14},
  timestamp       = {20181201T1030}
}

@Article{kirkpatrick2017-overcoming,
  author          = {Kirkpatrick, James and Pascanu, Razvan and Rabinowitz, Neil and Veness, Joel and Desjardins, Guillaume and Rusu, Andrei
                  A and Milan, Kieran and Quan, John and Ramalho, Tiago and Grabska-Barwinska, Agnieszka and others},
  title           = {Overcoming Catastrophic Forgetting in Neural Networks},
  journaltitle    = {Proceedings of the National Academy of Sciences},
  year            = 2017,
  pages           = 201611835,
  journal         = {Proceedings of the National Academy of Sciences},
  keywords        = {continual learning, forget},
  publisher       = {National Acad Sciences},
  timestamp       = {20181201T1030}
}

@InProceedings{kiros2015-skip,
  author          = {Kiros, Ryan and Zhu, Yukun and Salakhutdinov, Ruslan R and Zemel, Richard and Urtasun, Raquel and Torralba, Antonio and
                  Fidler, Sanja},
  title           = {Skip-thought vectors},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {3294--3302},
  timestamp       = {20181201T1030}
}

@Article{kitano1990-designing,
  author          = {Kitano, Hiroaki},
  title           = {Designing Neural Networks Using Genetic Algorithms With Graph Generation System},
  journaltitle    = {Complex Systems Journal},
  year            = 1990,
  volume          = 4,
  pages           = {461--476},
  journal         = {Complex Systems Journal},
  timestamp       = {20181201T1030}
}

@InProceedings{kitano1990-empirical,
  author          = {Kitano, Hiroaki},
  title           = {Empirical Studies on the Speed of Convergence of Neural Network Training Using Genetic Algorithms},
  year            = 1990,
  booktitle       = {Proceedings of the Eighth National Conference on Artificial Intelligence - Volume 2},
  series          = {AAAI'90},
  publisher       = {AAAI Press},
  location        = {Boston, Massachusetts},
  isbn            = {0-262-51057-X},
  pages           = {789--795},
  url             = {http://dl.acm.org/citation.cfm?id=1865609.1865618},
  acmid           = 1865618,
  numpages        = 7,
  timestamp       = {20181201T1030}
}

@Article{kitaoka2004-contrast,
  author          = {Kitaoka, Akiyoshi and Pinna, Baingio and Brelstaff, Gavin},
  title           = {Contrast Polarities Determine the Direction of Caf{\'e} Wall Tilts},
  journaltitle    = {Perception},
  year            = 2004,
  volume          = 33,
  number          = 1,
  pages           = {11--20},
  journal         = {Perception},
  publisher       = {SAGE Publications Sage UK: London, England},
  timestamp       = {20181201T1030}
}

@Article{klambauer2017-self,
  author          = {{Klambauer}, G. and {Unterthiner}, T. and {Mayr}, A. and {Hochreiter}, S.},
  title           = {{Self-Normalizing Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.02515},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {selu, scaled exponential linear units, activation, feedforward, normalizing},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{klein2017-opennmt,
  author          = {{Klein}, G. and {Kim}, Y. and {Deng}, Y.  and {Senellart}, J. and {Rush}, A.~M.},
  title           = {{OpenNMT: Open-Source Toolkit for Neural Machine Translation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  eprint          = {1701.02810},
  journal         = {ArXiv e-prints},
  timestamp       = {20181201T1030}
}

@Article{kleinberg2015-prediction,
  author          = {Kleinberg, Jon and Ludwig, Jens and Mullainathan, Sendhil and Obermeyer, Ziad},
  title           = {Prediction Policy Problems},
  journaltitle    = {American Economic Review},
  year            = 2015,
  volume          = 105,
  number          = 5,
  month           = {May},
  pages           = {491-95},
  doi             = {10.1257/aer.p20151023},
  url             = {https://doi.org/10.1257/aer.p20151023},
  journal         = {American Economic Review},
  timestamp       = {20181201T1030}
}

@InProceedings{klivans2006-cryptographic,
  author          = {Klivans, Adam R and Sherstov, Alexander A},
  title           = {Cryptographic hardness for learning intersections of halfspaces},
  year            = 2006,
  booktitle       = {2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06)},
  organization    = {IEEE},
  pages           = {553--562},
  timestamp       = {20181201T1030}
}

@InProceedings{koch2015-siamese,
  author          = {Koch, Gregory and Zemel, Richard and Salakhutdinov, Ruslan},
  title           = {Siamese neural networks for one-shot image recognition},
  year            = 2015,
  booktitle       = {ICML Deep Learning Workshop},
  volume          = 2,
  timestamp       = {20181201T1030}
}

@Misc{koehn1994-combining,
  author          = {Koehn, Philipp},
  title           = {Combining Genetic Algorithms and Neural Networks: The Encoding Problem},
  year            = 1994,
  publisher       = {Citeseer},
  timestamp       = {20181201T1030}
}

@InProceedings{koehn2003-statistical,
  author          = {Koehn, Philipp and Och, Franz Josef and Marcu, Daniel},
  title           = {Statistical phrase-based translation},
  year            = 2003,
  booktitle       = {Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on
                  Human Language Technology-Volume 1},
  organization    = {Association for Computational Linguistics},
  pages           = {48--54},
  timestamp       = {20181201T1030}
}

@InCollection{koester2017-flexpoint,
  author          = {K{\"o}ster, Urs and Webb, Tristan and Wang, Xin and Nassar, Marcel and Bansal, Arjun K and Constable, William and
                  Elibol, Oguz and Hall, Stewart and Hornof, Luke and Khosrowshahi, Amir and Kloss, Carey and Pai, Ruby J and Rao, Naveen},
  title           = {Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1740--1750},
  url             = {http://papers.nips.cc/paper/6771-flexpoint-an-adaptive-numerical-format-for-efficient-training-of-deep-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{kohonen2013-essentials,
  author          = {Kohonen, Teuvo},
  title           = {Essentials of the Self-Organizing Map},
  journaltitle    = {Neural Networks},
  year            = 2013,
  volume          = 37,
  pages           = {52--65},
  journal         = {Neural Networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@InProceedings{konda2000-actor,
  author          = {Konda, Vijay R and Tsitsiklis, John N},
  title           = {Actor-critic algorithms},
  year            = 2000,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1008--1014},
  keywords        = {rl},
  timestamp       = {20181201T1030}
}

@InProceedings{kontschieder2015-deep,
  author          = {P. Kontschieder and M. Fiterau and A. Criminisi and S. R. Bul{\'o}},
  title           = {Deep Neural Decision Forests},
  year            = 2015,
  booktitle       = {2015 IEEE International Conference on Computer Vision (ICCV)},
  month           = {Dec},
  pages           = {1467-1475},
  doi             = {10.1109/ICCV.2015.172},
  url             = {https://doi.org/10.1109/ICCV.2015.172},
  keywords        = {computer vision;convolution;decision trees;image representation;learning (artificial intelligence);neural
                  nets;optimisation;classification tree;computer vision;deep convolutional network;deep neural decision forest;machine
                  learning;parameter optimization;representation learning functionality;Computer vision;Decision
                  trees;Optimization;Routing;Stochastic processes;Training;Vegetation},
  timestamp       = {20181201T1030}
}

@Article{koppejan2011-neuroevolutionary,
  author          = {Koppejan, Rogier and Whiteson, Shimon},
  title           = {Neuroevolutionary Reinforcement Learning for Generalized Control of Simulated Helicopters},
  journaltitle    = {Evolutionary intelligence},
  year            = 2011,
  volume          = 4,
  number          = 4,
  pages           = {219--241},
  journal         = {Evolutionary intelligence},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@InCollection{korattikara2015-bayesian,
  author          = {Korattikara Balan, Anoop and Rathod, Vivek and Murphy, Kevin P and Welling, Max},
  title           = {Bayesian dark knowledge},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3438--3446},
  url             = {http://papers.nips.cc/paper/5965-bayesian-dark-knowledge.pdf},
  timestamp       = {20181201T1030}
}

@Article{kos2017-adversarial,
  author          = {{Kos}, J. and {Fischer}, I. and {Song}, D.},
  title           = {{Adversarial Examples for Generative models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.06832},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack, generative model, vae, gan},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{kos2017-delving,
  author          = {{Kos}, J. and {Song}, D.},
  title           = {{Delving Into Adversarial Attacks on Deep policies}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.06452},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{koutnik2013-evolving,
  author          = {Koutn{\'\i}k, Jan and Cuccu, Giuseppe and Schmidhuber, J{\"u}rgen and Gomez, Faustino},
  title           = {Evolving large-scale neural networks for vision-based reinforcement learning},
  year            = 2013,
  booktitle       = {Proceedings of the 15th annual conference on Genetic and evolutionary computation},
  organization    = {ACM},
  pages           = {1061--1068},
  timestamp       = {20181201T1030}
}

@Article{koutnik2014-clockwork,
  author          = {Koutnik, Jan and Greff, Klaus and Gomez, Faustino and Schmidhuber, Juergen},
  title           = {A Clockwork Rnn},
  journaltitle    = {arXiv preprint arXiv:1402.3511},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1402.3511},
  timestamp       = {20181201T1030}
}

@InProceedings{koza1991-genetic,
  author          = {J. R. Koza and J. P. Rice},
  title           = {Genetic generation of both the weights and architecture for a neural network},
  year            = 1991,
  booktitle       = {Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on},
  volume          = {ii},
  month           = {Jul},
  pages           = {397-404 vol.2},
  doi             = {10.1109/IJCNN.1991.155366},
  url             = {https://doi.org/10.1109/IJCNN.1991.155366},
  keywords        = {LISP;digital arithmetic;genetic algorithms;neural nets;LISP symbolic expressions;connectivity;genetic
                  programming;layers;neural net architecture;neural net weights;one-bit adder;performance;processing elements;Computational
                  modeling;Computer architecture;Computer science;Genetic algorithms;Genetic programming;Knowledge based
                  systems;Laboratories;Machine learning;Neural networks;Shape},
  timestamp       = {20181201T1030}
}

@Book{koza1992-genetic,
  author          = {Koza, John R.},
  title           = {Genetic Programming: On the Programming of Computers by Means of Natural Selection},
  year            = 1992,
  publisher       = {MIT Press},
  isbn            = {0-262-11170-5},
  address         = {Cambridge, MA, USA},
  timestamp       = {20181201T1030}
}

@Article{kraska2017-case,
  author          = {{Kraska}, T. and {Beutel}, A. and {Chi}, E.~H. and {Dean}, J. and {Polyzotis}, N.},
  title           = {{The Case for Learned Index Structures}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.01208},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171201208K},
  archiveprefix   = "arXiv",
  keywords        = {index, btree, hash},
  primaryclass    = "cs.DB",
  timestamp       = {20181201T1030}
}

@Article{krause2016-multiplicative,
  author          = {Ben Krause and Liang Lu and Iain Murray and Steve Renals},
  title           = {Multiplicative {LSTM} for Sequence Modelling},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.07959},
  eprint          = {1609.07959},
  url             = {http://arxiv.org/abs/1609.07959},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/KrauseLMR16},
  keywords        = {mlstm},
  timestamp       = {20181201T1030}
}

@Article{krauss2018-statistical,
  author          = {Krauss, Patrick and Metzner, Claus and Schilling, Achim and Tziridis, Konstantin and Traxdorf, Maximilian and
                  Wollbrink, Andreas and Rampp, Stefan and Pantev, Christo and Schulze, Holger},
  title           = {A Statistical Method for Analyzing and Comparing Spatiotemporal Cortical Activation Patterns},
  journaltitle    = {Scientific reports},
  year            = 2018,
  volume          = 8,
  number          = 1,
  pages           = 5433,
  journal         = {Scientific reports},
  keywords        = {gdv, mcs, generalized discrimination value,multidimensional cluster statistics},
  publisher       = {Nature Publishing Group},
  timestamp       = {20181201T1030}
}

@Article{krauth1989-storage,
  author          = {Krauth, Werner and M{\'e}zard, Marc},
  title           = {Storage Capacity of Memory Networks With Binary Couplings},
  journaltitle    = {Journal de Physique},
  year            = 1989,
  volume          = 50,
  number          = 20,
  pages           = {3057--3066},
  journal         = {Journal de Physique},
  keywords        = {binary, capacity, nn},
  publisher       = {Soci{\'e}t{\'e} fran{\c{c}}aise de physique},
  timestamp       = {20181201T1030}
}

@Article{kriegman2017-how,
  author          = {{Kriegman}, S. and {Cheney}, N. and {Bongard}, J.},
  title           = {{How Morphological Development Can Guide evolution}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.07387},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171107387K},
  archiveprefix   = "arXiv",
  keywords        = {Quantitative Biology - Populations and Evolution, Computer Science - Artificial Intelligence, Computer Science -
                  Robotics},
  primaryclass    = "q-bio.PE",
  timestamp       = {20181201T1030}
}

@InProceedings{kriegman2017-simulating,
  author          = {Kriegman, Sam and Cappelle, Collin and Corucci, Francesco and Bernatskiy, Anton and Cheney, Nick and Bongard, Josh C},
  title           = {Simulating the evolution of soft and rigid-body robots},
  year            = 2017,
  booktitle       = {Proceedings of the Genetic and Evolutionary Computation Conference Companion},
  organization    = {ACM},
  pages           = {1117--1120},
  timestamp       = {20181201T1030}
}

@Article{krishna2017-visual,
  author          = {Krishna, Ranjay and Zhu, Yuke and Groth, Oliver and Johnson, Justin and Hata, Kenji and Kravitz, Joshua and Chen,
                  Stephanie and Kalantidis, Yannis and Li, Li-Jia and Shamma, David A and others},
  title           = {Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations},
  journaltitle    = {International Journal of Computer Vision},
  year            = 2017,
  volume          = 123,
  number          = 1,
  pages           = {32--73},
  journal         = {International Journal of Computer Vision},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@InProceedings{krizhevsky2012-imagenet,
  author          = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
  title           = {Imagenet classification with deep convolutional neural networks},
  year            = 2012,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1097--1105},
  keywords        = {alexnet},
  timestamp       = {20181201T1030}
}

@Article{krueger2016-zoneout,
  author          = {{Krueger}, D. and {Maharaj}, T. and {Kram{\'a}r}, J. and {Pezeshki}, M. and {Ballas}, N. and {Ke}, N.~R. and {Goyal},
                  A. and {Bengio}, Y. and {Larochelle}, H. and {Courville}, A. and {Pal}, C.},
  title           = {{Zoneout: Regularizing Rnns By Randomly Preserving Hidden Activations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.01305},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Neural and Evolutionary Computing, Computer Science - Computation and Language, Computer Science -
                  Learning},
  timestamp       = {20181201T1030}
}

@Article{krueger2017-deep,
  author          = {Krueger, David and Ballas, Nicolas and Jastrzebski, Stanislaw and Arpit, Devansh and Kanwal, Maxinder S and Maharaj,
                  Tegan and Bengio, Emmanuel and Fischer, Asja and Courville, Aaron},
  title           = {Deep Nets Don't Learn Via Memorization},
  journaltitle    = {ICLR 2017 Workshop},
  year            = 2017,
  timestamp       = {20181201T1030}
}

@Article{krzakala2007-gibbs,
  author          = {Krzaka{\l}a, Florent and Montanari, Andrea and Ricci-Tersenghi, Federico and Semerjian, Guilhem and Zdeborov{\'a},
                  Lenka},
  title           = {Gibbs States and the Set of Solutions of Random Constraint Satisfaction Problems},
  journaltitle    = {Proceedings of the National Academy of Sciences},
  year            = 2007,
  volume          = 104,
  number          = 25,
  pages           = {10318--10323},
  journal         = {Proceedings of the National Academy of Sciences},
  publisher       = {National Acad Sciences},
  timestamp       = {20181201T1030}
}

@Unpublished{kuleshov2018-adversarial,
  author          = {Volodymyr Kuleshov and Shantanu Thakoor and Tingfung Lau and Stefano Ermon},
  title           = {Adversarial Examples for Natural Language Classification Problems},
  year            = 2018,
  url             = {https://openreview.net/forum?id=r1QZ3zbAZ},
  keywords        = {adversarial, attack, text},
  timestamp       = {20181201T1030}
}

@InCollection{kulkarni2015-deep,
  author          = {Kulkarni, Tejas D and Whitney, William F. and Kohli, Pushmeet and Tenenbaum, Josh},
  title           = {Deep Convolutional Inverse Graphics Network},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2539--2547},
  url             = {http://papers.nips.cc/paper/5851-deep-convolutional-inverse-graphics-network.pdf},
  timestamp       = {20181201T1030}
}

@Article{kurakin2016-adversarial-examples,
  author          = {{Kurakin}, A. and {Goodfellow}, I. and {Bengio}, S.},
  title           = {{Adversarial Examples in the Physical world}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jul,
  eprint          = {1607.02533},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, fgsm, tgsm},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{kurakin2016-adversarial-machine,
  author          = {Alexey Kurakin and Ian J. Goodfellow and Samy Bengio},
  title           = {Adversarial Machine Learning At Scale},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.01236},
  url             = {http://arxiv.org/abs/1611.01236},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/KurakinGB16a},
  keywords        = {adversarial, label leaking, model capacity},
  timestamp       = {20181201T1030}
}

@InProceedings{kushilevitz1998-efficient,
  author          = {Kushilevitz, Eyal and Ostrovsky, Rafail and Rabani, Yuval},
  title           = {Efficient Search for Approximate Nearest Neighbor in High Dimensional Spaces},
  year            = 1998,
  booktitle       = {Proceedings of the Thirtieth Annual ACM Symposium on Theory of Computing},
  series          = {STOC '98},
  publisher       = {ACM},
  location        = {Dallas, Texas, USA},
  isbn            = {0-89791-962-9},
  pages           = {614--623},
  doi             = {10.1145/276698.276877},
  url             = {https://doi.org/10.1145/276698.276877},
  acmid           = 276877,
  address         = {New York, NY, USA},
  numpages        = 10,
  timestamp       = {20181201T1030}
}

@InProceedings{kusner2015-from,
  author          = {Kusner, Matt and Sun, Yu and Kolkin, Nicholas and Weinberger, Kilian},
  title           = {From word embeddings to document distances},
  year            = 2015,
  booktitle       = {International Conference on Machine Learning},
  pages           = {957--966},
  keywords        = {wmd},
  timestamp       = {20181201T1030}
}

@Article{kwan1993-multiplierless,
  author          = {H. K. Kwan and C. Z. Tang},
  title           = {Multiplierless Multilayer Feedforward Neural Network Design Suitable for Continuous Input-Output Mapping},
  journaltitle    = {Electronics Letters},
  year            = 1993,
  volume          = 29,
  number          = 14,
  month           = {July},
  pages           = {1259-1260},
  issn            = {0013-5194},
  doi             = {10.1049/el:19930841},
  url             = {https://doi.org/10.1049/el:19930841},
  journal         = {Electronics Letters},
  keywords        = {backpropagation;feedforward neural nets;MFNN;computational speed;continuous input-output mapping;digital hardware
                  cost;multiplierless multilayer feedforward neural network;noisy vectors;recall accuracy},
  timestamp       = {20181201T1030}
}

@Article{kwon2018-friend,
  author          = "Hyun Kwon and Yongchul Kim and Ki-Woong Park and Hyunsoo Yoon and Daeseon Choi",
  title           = {Friend-Safe Evasion Attack: an Adversarial Example That Is Correctly Recognized By a Friendly Classifier},
  journaltitle    = "Computers \& Security",
  year            = 2018,
  volume          = 78,
  pages           = "380 - 397",
  issn            = "0167-4048",
  doi             = "https://doi.org/10.1016/j.cose.2018.07.015",
  url             = {https://doi.org/https://doi.org/10.1016/j.cose.2018.07.015},
  journal         = "Computers \& Security",
  keywords        = {adversarial, attack},
  timestamp       = {20181201T1030}
}

@Article{lake2015-human,
  author          = {Lake, Brenden M. and Salakhutdinov, Ruslan and Tenenbaum, Joshua B.},
  title           = {Human-Level Concept Learning Through Probabilistic Program Induction},
  journaltitle    = {Science},
  year            = 2015,
  volume          = 350,
  number          = 6266,
  pages           = {1332-1338},
  doi             = {10.1126/science.aab3050},
  eprint          = {http://www.sciencemag.org/content/350/6266/1332.full.pdf},
  url             = {https://doi.org/10.1126/science.aab3050},
  journal         = {Science},
  timestamp       = {20181201T1030}
}

@Article{lake2016-building,
  author          = {Brenden M. Lake and Tomer D. Ullman and Joshua B. Tenenbaum and Samuel J. Gershman},
  title           = {Building Machines That Learn and Think Like People},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.00289},
  url             = {http://arxiv.org/abs/1604.00289},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LakeUTG16},
  timestamp       = {20181201T1030}
}

@Article{lake2017-still,
  author          = {{Lake}, B.~M. and {Baroni}, M.},
  title           = {{Still Not Systematic After All These Years: on the Compositional Skills of Sequence-To-Sequence Recurrent networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1711.00350},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171100350L},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{lamb2016-professor,
  author          = {Lamb, Alex M and GOYAL, Anirudh Goyal ALIAS PARTH and Zhang, Ying and Zhang, Saizheng and Courville, Aaron C and
                  Bengio, Yoshua},
  title           = {Professor forcing: A new algorithm for training recurrent networks},
  year            = 2016,
  booktitle       = {Advances In Neural Information Processing Systems},
  pages           = {4601--4609},
  keywords        = {exposure bias, rnn, professor forcing},
  timestamp       = {20181201T1030}
}

@Article{lamb2018-fortified,
  author          = {{Lamb}, A. and {Binas}, J. and {Goyal}, A. and {Serdyuk}, D. and {Subramanian}, S. and {Mitliagkas}, I. and {Bengio},
                  Y.},
  title           = {{Fortified Networks: Improving the Robustness of Deep Networks By Modeling the Manifold of Hidden Representations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = apr,
  eprint          = {1804.02485},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180402485L},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InCollection{lample2017-fader,
  author          = {Lample, Guillaume and Zeghidour, Neil and Usunier, Nicolas and Bordes, Antoine and DENOYER, Ludovic and Ranzato,
                  Marc\textquotesingle Aurelio},
  title           = {Fader Networks:Manipulating Images by Sliding Attributes},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5969--5978},
  url             = {http://papers.nips.cc/paper/7178-fader-networksmanipulating-images-by-sliding-attributes.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{lample2018-unsupervised,
  author          = {Guillaume Lample and Alexis Conneau and Ludovic Denoyer and Marc'Aurelio Ranzato},
  title           = {Unsupervised Machine Translation Using Monolingual Corpora Only},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=rkYTTf-AZ},
  timestamp       = {20181201T1030}
}

@Article{landauer1997-solution,
  author          = {Landauer, Thomas K and Dumais, Susan T},
  title           = {A Solution To Plato's Problem: the Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of
                  Knowledge.},
  journaltitle    = {Psychological review},
  year            = 1997,
  volume          = 104,
  number          = 2,
  pages           = 211,
  journal         = {Psychological review},
  publisher       = {US: American Psychological Association},
  timestamp       = {20190109T1302}
}

@InProceedings{larochelle2008-classification,
  author          = {Larochelle, Hugo and Bengio, Yoshua},
  title           = {Classification Using Discriminative Restricted Boltzmann Machines},
  year            = 2008,
  booktitle       = {Proceedings of the 25th International Conference on Machine Learning},
  series          = {ICML '08},
  publisher       = {ACM},
  location        = {Helsinki, Finland},
  isbn            = {978-1-60558-205-4},
  pages           = {536--543},
  doi             = {10.1145/1390156.1390224},
  url             = {https://doi.org/10.1145/1390156.1390224},
  acmid           = 1390224,
  address         = {New York, NY, USA},
  numpages        = 8,
  timestamp       = {20181201T1030}
}

@Article{larochelle2012-learning,
  author          = {Larochelle, Hugo and Mandel, Michael and Pascanu, Razvan and Bengio, Yoshua},
  title           = {Learning Algorithms for the Classification Restricted Boltzmann Machine},
  journaltitle    = {J. Mach. Learn. Res.},
  year            = 2012,
  volume          = 13,
  number          = 1,
  month           = mar,
  pages           = {643--669},
  issn            = {1532-4435},
  url             = {http://dl.acm.org/citation.cfm?id=2503308.2188407},
  journal         = {J. Mach. Learn. Res.},
  acmid           = 2188407,
  issue_date      = {January 2012},
  keywords        = {classification, discriminative learning, generative learning, restricted Boltzmannmachine},
  numpages        = 27,
  publisher       = {JMLR.org},
  timestamp       = {20181201T1030}
}

@Article{larsen2015-autoencoding,
  author          = {Larsen, Anders Boesen Lindbo and S{\o}nderby, S{\o}ren Kaae and Larochelle, Hugo and Winther, Ole},
  title           = {Autoencoding Beyond Pixels Using a Learned Similarity Metric},
  journaltitle    = {arXiv preprint arXiv:1512.09300},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1512.09300},
  keywords        = {vae, gan},
  timestamp       = {20181201T1030}
}

@Article{larsson2016-fractalnet,
  author          = {Gustav Larsson and Michael Maire and Gregory Shakhnarovich},
  title           = {Fractalnet: Ultra-Deep Neural Networks Without Residuals},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1605.07648},
  url             = {http://arxiv.org/abs/1605.07648},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LarssonMS16a},
  timestamp       = {20181201T1030}
}

@InProceedings{laskov2014-practical,
  author          = {Laskov, Pavel and others},
  title           = {Practical evasion of a learning-based classifier: A case study},
  year            = 2014,
  booktitle       = {Security and Privacy (SP), 2014 IEEE Symposium on},
  organization    = {IEEE},
  pages           = {197--211},
  keywords        = {adversarial, attack},
  timestamp       = {20181201T1030}
}

@InCollection{laub2007-inducing,
  author          = {Julian Laub and M{\"u}ller, Klaus-Robert and Felix A. Wichmann and Macke, Jakob H},
  title           = {Inducing Metric Violations in Human Similarity Judgements},
  year            = 2007,
  booktitle       = {Advances in Neural Information Processing Systems 19},
  editor          = {B. Sch{\"o}lkopf and J. C. Platt and T. Hoffman},
  publisher       = {MIT Press},
  pages           = {777--784},
  url             = {http://papers.nips.cc/paper/3090-inducing-metric-violations-in-human-similarity-judgements.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{lawrence2002-note,
  author          = {Lawrence, Neil D},
  title           = {Note Relevance Determination},
  year            = 2002,
  booktitle       = {Neural Nets WIRN Vietri-01},
  publisher       = {Springer},
  pages           = {128--133},
  keywords        = {pruning, bayesian},
  timestamp       = {20181201T1030}
}

@Article{lawrence2017-living,
  author          = {{Lawrence}, N.~D.},
  title           = {{Living Together: Mind and Machine Intelligence}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.07996},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@Book{lawvere2009-conceptual,
  author          = {Lawvere, F William and Schanuel, Stephen H},
  title           = {Conceptual mathematics: a first introduction to categories},
  year            = 2009,
  publisher       = {Cambridge University Press},
  timestamp       = {20181201T1030}
}

@Book{layek2015-introduction,
  author          = {Layek, GC},
  title           = {An Introduction to Dynamical Systems and Chaos},
  year            = 2015,
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{lazaridou2015-unveiling,
  author          = {Angeliki Lazaridou and Dat Tien Nguyen and Raffaella Bernardi and Marco Baroni},
  title           = {Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.03500},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{lazarow2017-introspective,
  author          = {Justin Lazarow and Long Jin and Zhuowen Tu},
  title           = {Introspective Generative Modeling: Decide Discriminatively},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.07820},
  url             = {http://arxiv.org/abs/1704.07820},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LazarowJT17},
  timestamp       = {20181201T1030}
}

@InProceedings{le2013-fastfood,
  author          = {Le, Quoc and Sarl{\'o}s, Tam{\'a}s and Smola, Alex},
  title           = {Fastfood-approximating kernel expansions in loglinear time},
  year            = 2013,
  booktitle       = {Proceedings of the international conference on machine learning},
  volume          = 85,
  timestamp       = {20181201T1030}
}

@Article{le2015-simple,
  author          = {Quoc V. Le and Navdeep Jaitly and Geoffrey E. Hinton},
  title           = {A Simple Way To Initialize Recurrent Networks of Rectified Linear Units},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1504.00941},
  url             = {http://arxiv.org/abs/1504.00941},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LeJH15},
  timestamp       = {20181201T1030}
}

@InProceedings{lebedev2016-fast,
  author          = {Lebedev, Vadim and Lempitsky, Victor},
  title           = {Fast convnets using group-wise brain damage},
  year            = 2016,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {2554--2564},
  keywords        = {brain damage, cnn, compression, mnist, imagenet},
  timestamp       = {20181201T1030}
}

@InProceedings{lecun1989-optimal,
  author          = {LeCun, Yann and Denker, John S and Solla, Sara A and Howard, Richard E and Jackel, Lawrence D},
  title           = {Optimal brain damage.},
  year            = 1989,
  booktitle       = {NIPs},
  volume          = 2,
  pages           = {598--605},
  keywords        = {pruning, saliency},
  timestamp       = {20181201T1030}
}

@Article{lecun1998-gradient,
  author          = {LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick},
  title           = {Gradient-Based Learning Applied To Document Recognition},
  journaltitle    = {Proceedings of the IEEE},
  year            = 1998,
  volume          = 86,
  number          = 11,
  pages           = {2278--2324},
  journal         = {Proceedings of the IEEE},
  keywords        = {lenet},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Report{lecun2004-dave,
  author          = {LeCun, Y and Cosatto, E and Ben, J and Muller, U and Flepp, B},
  title           = {DAVE: Autonomous off-road vehicle control using end-to-end learning},
  type            = {tech report},
  institution     = {Technical Report DARPA-IPTO Final Report, Courant Institute/CBLL,
                  http://www. cs. nyu. edu/yann/research/dave/index. html},
  year            = 2004,
  keywords        = {dave},
  timestamp       = {20181201T1030}
}

@Article{lecun2006-tutorial,
  author          = {LeCun, Yann and Chopra, Sumit and Hadsell, Raia and Ranzato, M and Huang, F},
  title           = {A Tutorial on Energy-Based Learning},
  journaltitle    = {Predicting structured data},
  year            = 2006,
  volume          = 1,
  pages           = 0,
  journal         = {Predicting structured data},
  keywords        = {energy based model, ebm},
  timestamp       = {20181201T1030}
}

@Misc{lecun2010-mnist,
  author          = {LeCun, Yann and Cortes, Corinna},
  title           = {{MNIST} handwritten digit database},
  year            = 2010,
  howpublished    = {http://yann.lecun.com/exdb/mnist/},
  url             = {http://yann.lecun.com/exdb/mnist/},
  added-at        = {2010-06-28T21:16:30.000+0200},
  biburl          = {http://www.bibsonomy.org/bibtex/25c6723dcce8057a5a41a5d7e12684930/mhwombat},
  groups          = {public},
  interhash       = {21b9d0558bd66279df9452562df6e6f3},
  intrahash       = {5c6723dcce8057a5a41a5d7e12684930},
  keywords        = {data, mnist},
  lastchecked     = {2010-02-22 00:36:34},
  timestamp       = {20181201T1030},
  username        = {mhwombat}
}

@Article{lecun2015-deep,
  author          = {LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
  title           = {Deep Learning},
  journaltitle    = {Nature},
  year            = 2015,
  volume          = 521,
  number          = 7553,
  month           = 5,
  pages           = {436--444},
  issn            = {0028-0836},
  doi             = {10.1038/nature14539},
  url             = {https://doi.org/10.1038/nature14539},
  journal         = {Nature},
  publisher       = {Nature Publishing Group},
  timestamp       = {20181201T1030}
}

@Article{lee2014-deeply,
  author          = {{Lee}, C.-Y. and {Xie}, S. and {Gallagher}, P. and {Zhang}, Z. and {Tu}, Z.},
  title           = {{Deeply-Supervised Nets}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = sep,
  eprint          = {1409.5185},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{lee2014-difference,
  author          = {Dong{-}Hyun Lee and Saizheng Zhang and Antoine Biard and Yoshua Bengio},
  title           = {Difference Target Propagation},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.7525},
  url             = {http://arxiv.org/abs/1412.7525},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LeeZBB14},
  timestamp       = {20181201T1030}
}

@Article{lee2016-fully,
  author          = {Jason Lee and Kyunghyun Cho and Thomas Hofmann},
  title           = {Fully Character-Level Neural Machine Translation Without Explicit Segmentation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1610.03017},
  journal         = {CoRR},
  keywords        = {nmt, char2char},
  timestamp       = {20181201T1030}
}

@Article{lee2016-sequential,
  author          = {Ji Young Lee and Franck Dernoncourt},
  title           = {Sequential Short-Text Classification With Recurrent and Convolutional Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.03827},
  url             = {http://arxiv.org/abs/1603.03827},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{lee2017-emergent,
  author          = {Lee, Jason and Cho, Kyunghyun and Weston, Jason and Kiela, Douwe},
  title           = {Emergent Translation in Multi-Agent Communication},
  journaltitle    = {arXiv preprint arXiv:1710.06922},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1710.06922},
  timestamp       = {20181201T1030}
}

@Article{lee2017-end,
  author          = {Lee, Kenton and He, Luheng and Lewis, Mike and Zettlemoyer, Luke},
  title           = {End-To-End Neural Coreference Resolution},
  keywords        = {data, coref},
  journaltitle    = {arXiv preprint arXiv:1707.07045},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.07045},
  timestamp       = {20190107T0952}
}

@Article{lee2017-generative,
  author          = {Hyeungill Lee and Sungyeob Han and Jungwoo Lee},
  title           = {Generative Adversarial Trainer: Defense To Adversarial Perturbations With {GAN}},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1705.03387},
  eprint          = {1705.03387},
  url             = {http://arxiv.org/abs/1705.03387},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/LeeHL17},
  keywords        = {adversarial, gan, defense},
  timestamp       = {20181201T1030}
}

@InProceedings{lee2017-muse,
  author          = {Guang-He Lee and Yun-Nung Chen},
  title           = {MUSE: Modularizing Unsupervised Sense Embeddings},
  year            = 2017,
  booktitle       = {EMNLP},
  timestamp       = {20181201T1030}
}

@InCollection{lee2017-overcoming,
  author          = {Lee, Sang-Woo and Kim, Jin-Hwa and Jun, Jaehyun and Ha, Jung-Woo and Zhang, Byoung-Tak},
  title           = {Overcoming Catastrophic Forgetting by Incremental Moment Matching},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4655--4665},
  url             = {http://papers.nips.cc/paper/7051-overcoming-catastrophic-forgetting-by-incremental-moment-matching.pdf},
  timestamp       = {20181201T1030}
}

@Article{lee2018-deterministic,
  author          = {{Lee}, J. and {Mansimov}, E. and {Cho}, K.},
  title           = {{Deterministic Non-Autoregressive Neural Sequence Modeling By Iterative Refinement}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.06901},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180206901L},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Computation and Language, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{leng2017-extremely,
  author          = {Cong Leng and Hao Li and Shenghuo Zhu and Rong Jin},
  title           = {Extremely Low Bit Neural Network: Squeeze the Last Bit Out With {ADMM}},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.09870},
  journal         = {CoRR},
  keywords        = {quantization, admm},
  timestamp       = {20181201T1030}
}

@Article{lerer2016-learning,
  author          = {Adam Lerer and Sam Gross and Rob Fergus},
  title           = {Learning Physical Intuition of Block Towers By Example},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.01312},
  url             = {http://arxiv.org/abs/1603.01312},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LererGF16},
  timestamp       = {20181201T1030}
}

@InProceedings{levine2018-deep,
  author          = {Yoav Levine and David Yakira and Nadav Cohen and Amnon Shashua},
  title           = {Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SywXXwJAb},
  timestamp       = {20181201T1030}
}

@InProceedings{levy2014-neural,
  author          = {Levy, Omer and Goldberg, Yoav},
  title           = {Neural word embedding as implicit matrix factorization},
  year            = 2014,
  booktitle       = {Advances in neural information processing systems},
  pages           = {2177--2185},
  timestamp       = {20181201T1030}
}

@InProceedings{li2002-dpf,
  author          = {Baitao Li and E. Chang and Ching-Tung Wu},
  title           = {DPF - a perceptual distance function for image retrieval},
  year            = 2002,
  booktitle       = {Proceedings. International Conference on Image Processing},
  volume          = 2,
  pages           = {II-597-II-600 vol.2},
  doi             = {10.1109/ICIP.2002.1040021},
  url             = {https://doi.org/10.1109/ICIP.2002.1040021},
  issn            = {1522-4880},
  timestamp       = {20181201T1030}
}

@InProceedings{li2007-ordinal,
  author          = {Li, Ling and Lin, Hsuan-Tien},
  title           = {Ordinal regression by extended binary classification},
  year            = 2007,
  booktitle       = {Advances in neural information processing systems},
  pages           = {865--872},
  keywords        = {learning to rank},
  timestamp       = {20181201T1030}
}

@InProceedings{li2008-mcrank,
  author          = {Li, Ping and Wu, Qiang and Burges, Christopher J},
  title           = {Mcrank: Learning to rank using multiple classification and gradient boosting},
  year            = 2008,
  booktitle       = {Advances in neural information processing systems},
  pages           = {897--904},
  keywords        = {learning to rank},
  timestamp       = {20181201T1030}
}

@InProceedings{li2014-scaling,
  author          = {Mu Li and David G. Anderson and Jun Woo Park and Alexander J. Smola and Amr Ahmed and Vanja Josifovski and James Long
                  and Eugene J. Shekita and Bor-Yiing Su},
  title           = {Scaling Distributed Machine Learning with the Parameter Server},
  year            = 2014,
  booktitle       = {Operating Systems Design and Implementation (OSDI)},
  pages           = {583--598},
  timestamp       = {20181201T1030}
}

@InProceedings{li2015-do,
  author          = {Jiwei Li and Daniel Jurafsky},
  title           = {Do Multi-Sense Embeddings Improve Natural Language Understanding?},
  year            = 2015,
  booktitle       = {EMNLP},
  timestamp       = {20181201T1030}
}

@Article{li2015-generative,
  author          = {Yujia Li and Kevin Swersky and Richard S. Zemel},
  title           = {Generative Moment Matching Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1502.02761},
  url             = {http://arxiv.org/abs/1502.02761},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LiSZ15},
  timestamp       = {20181201T1030}
}

@InCollection{li2015-max,
  author          = {Li, Chongxuan and Zhu, Jun and Shi, Tianlin and Zhang, Bo},
  title           = {Max-Margin Deep Generative Models},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1837--1845},
  url             = {http://papers.nips.cc/paper/5958-max-margin-deep-generative-models.pdf},
  timestamp       = {20181201T1030}
}

@Article{li2015-visualizing,
  author          = {Jiwei Li and Xinlei Chen and Eduard H. Hovy and Dan Jurafsky},
  title           = {Visualizing and Understanding Neural Models in {NLP}},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.01066},
  url             = {http://arxiv.org/abs/1506.01066},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LiCHJ15},
  timestamp       = {20181201T1030}
}

@InProceedings{li2016-learning,
  author          = {Qi Li and Tianshi Li and Baobao Chang},
  title           = {Learning Word Sense Embeddings from Word Sense Definitions},
  year            = 2016,
  booktitle       = {NLPCC/ICCPOL},
  timestamp       = {20181201T1030}
}

@InProceedings{li2016-lightrnn,
  author          = {Li, Xiang and Qin, Tao and Yang, Jian and Liu, Tie-Yan},
  title           = {LightRNN: Memory and computation-efficient recurrent neural networks},
  keywords        = {lightrnn},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {4385--4393},
  timestamp       = {20190107T1415}
}

@Article{li2016-multi,
  author          = {Qi Li and Tianshi Li and Baobao Chang},
  title           = {Multi-Phase Word Sense Embedding Learning Using a Corpus and a Lexical Ontology},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.04835},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InProceedings{li2016-online,
  author          = {Li, Chris Junchi and Wang, Zhaoran and Liu, Han},
  title           = {Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {4961--4969},
  timestamp       = {20181201T1030}
}

@Article{li2016-pruning,
  author          = {Hao Li and Asim Kadav and Igor Durdanovic and Hanan Samet and Hans Peter Graf},
  title           = {Pruning Filters for Efficient Convnets},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1608.08710},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1030}
}

@Article{li2016-ternary,
  author          = {Fengfu Li and Bin Liu},
  title           = {Ternary Weight Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1605.04711},
  url             = {http://arxiv.org/abs/1605.04711},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LiL16},
  keywords        = {quantization, ternary, mnist, imagenet},
  timestamp       = {20181201T1030}
}

@Article{li2016-understanding,
  author          = {Jiwei Li and Will Monroe and Dan Jurafsky},
  title           = {Understanding Neural Networks Through Representation Erasure},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.08220},
  eprint          = {1612.08220},
  url             = {http://arxiv.org/abs/1612.08220},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/LiMJ16a},
  keywords        = {interpret},
  timestamp       = {20181201T1030}
}

@InProceedings{li2016-visualizing,
  author          = {Li, Jiwei and Chen, Xinlei and Hovy, Eduard and Jurafsky, Dan},
  title           = {Visualizing and Understanding Neural Models in NLP},
  year            = 2016,
  booktitle       = {Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:
                  Human Language Technologies},
  publisher       = {Association for Computational Linguistics},
  location        = {San Diego, California},
  pages           = {681--691},
  doi             = {10.18653/v1/N16-1082},
  url             = {https://doi.org/10.18653/v1/N16-1082},
  timestamp       = {20181230T1437}
}

@Article{li2017-adversarial,
  author          = {Jiwei Li and Will Monroe and Tianlin Shi and Alan Ritter and Dan Jurafsky},
  title           = {Adversarial Learning for Neural Dialogue Generation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1701.06547},
  journal         = {CoRR},
  keywords        = {gan, rl},
  timestamp       = {20181201T1030}
}

@InCollection{li2017-convergence,
  author          = {Li, Yuanzhi and Yuan, Yang},
  title           = {Convergence Analysis of Two-layer Neural Networks with ReLU Activation},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {597--607},
  url             = {http://papers.nips.cc/paper/6662-convergence-analysis-of-two-layer-neural-networks-with-relu-activation.pdf},
  timestamp       = {20181201T1030}
}

@Article{li2017-learning,
  author          = {Li, Jiwei and Monroe, Will and Jurafsky, Dan},
  title           = {Learning To Decode for Future Success},
  journaltitle    = {arXiv preprint arXiv:1701.06549},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1701.06549},
  timestamp       = {20181201T1030}
}

@InProceedings{li2017-stochastic,
  author          = {Li, Qianxiao and Tai, Cheng and Weinan, E},
  title           = {Stochastic modified equations and adaptive stochastic gradient algorithms},
  year            = 2017,
  booktitle       = {International Conference on Machine Learning},
  pages           = {2101--2110},
  timestamp       = {20181201T1030}
}

@InProceedings{li2017-towards,
  author          = {Li, Hao and De, Soham and Xu, Zheng and Studer, Christoph and Samet, Hanan and Goldstein, Tom},
  title           = {Towards a Deeper Understanding of Training Quantized Neural Networks},
  year            = 2017,
  booktitle       = {Proceedings of the 34nd International Conference on Machine Learning (ICML-17) Workshop},
  keywords        = {compression, theory},
  timestamp       = {20181201T1030}
}

@InCollection{li2017-training,
  author          = {Li, Hao and De, Soham and Xu, Zheng and Studer, Christoph and Samet, Hanan and Goldstein, Tom},
  title           = {Training Quantized Nets: A Deeper Understanding},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5813--5823},
  url             = {http://papers.nips.cc/paper/7163-training-quantized-nets-a-deeper-understanding.pdf},
  keywords        = {quantization, theory, risk minimization, binary connect, stochastic rounding, markov chain},
  timestamp       = {20181201T1030}
}

@InCollection{li2017-universal,
  author          = {Li, Yijun and Fang, Chen and Yang, Jimei and Wang, Zhaowen and Lu, Xin and Yang, Ming-Hsuan},
  title           = {Universal Style Transfer via Feature Transforms},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {385--395},
  url             = {http://papers.nips.cc/paper/6642-universal-style-transfer-via-feature-transforms.pdf},
  timestamp       = {20181201T1030}
}

@Article{li2018-adaptive,
  author          = {{Li}, R. and {Wang}, S. and {Zhu}, F. and {Huang}, J.},
  title           = {{Adaptive Graph Convolutional Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.03226},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180103226L},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InProceedings{li2018-measuring,
  author          = {Chunyuan Li and Heerad Farkhoor and Rosanne Liu and Jason Yosinski},
  title           = {Measuring the Intrinsic Dimension of Objective Landscapes},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=ryup8-WCW},
  timestamp       = {20181201T1030}
}

@InCollection{liang2015-convolutional,
  author          = {Liang, Ming and Hu, Xiaolin and Zhang, Bo},
  title           = {Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {937--945},
  url             = {http://papers.nips.cc/paper/5634-convolutional-neural-networks-with-intra-layer-recurrent-connections-for-scene-labeling.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{liang2015-evolutionary,
  author          = {Liang, Jason Zhi and Miikkulainen, Risto},
  title           = {Evolutionary bilevel optimization for complex control tasks},
  year            = 2015,
  booktitle       = {Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation},
  organization    = {ACM},
  pages           = {871--878},
  timestamp       = {20181201T1030}
}

@Article{liang2017-deep,
  author          = {Liang, Bin and Li, Hongcheng and Su, Miaoqiang and Bian, Pan and Li, Xirong and Shi, Wenchang},
  title           = {Deep Text Classification Can Be Fooled},
  journaltitle    = {arXiv preprint arXiv:1704.08006},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1704.08006},
  keywords        = {adversarial, text},
  timestamp       = {20181201T1030}
}

@Article{liang2017-detecting,
  author          = {Liang, Bin and Li, Hongcheng and Su, Miaoqiang and Li, Xirong and Shi, Wenchang and Wang, Xiaofeng},
  title           = {Detecting Adversarial Examples in Deep Networks With Adaptive Noise Reduction},
  journaltitle    = {arXiv preprint arXiv:1705.08378},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.08378},
  keywords        = {adversarial, defense},
  timestamp       = {20181201T1030}
}

@InProceedings{liang2018-enhancing,
  author          = {Shiyu Liang and Yixuan Li and R. Srikant},
  title           = {Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=H1VGkIxRZ},
  timestamp       = {20181201T1030}
}

@Article{liao2018-backdoor,
  author          = {{Liao}, C. and {Zhong}, H. and {Squicciarini}, A. and {Zhu}, S. and {Miller}, D.},
  title           = {{Backdoor Embedding in Convolutional Neural Network Models Via Invisible Perturbation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.10307},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180810307L},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Cryptography and Security, Computer Science - Machine Learning, Statistics - Machine Learning},
  primaryclass    = "cs.CR",
  timestamp       = {20181201T1030}
}

@InCollection{lilley2005-neural,
  author          = {Lilley, Matthew and Frean, Marcus},
  title           = {Neural Networks: A Replacement for Gaussian Processes?},
  year            = 2005,
  booktitle       = {Intelligent Data Engineering and Automated Learning - IDEAL 2005},
  editor          = {Gallagher, Marcus and Hogan, JamesP. and Maire, Frederic},
  language        = {English},
  volume          = 3578,
  series          = {Lecture Notes in Computer Science},
  publisher       = {Springer Berlin Heidelberg},
  isbn            = {978-3-540-26972-4},
  pages           = {195-202},
  doi             = {10.1007/11508069_26},
  url             = {https://doi.org/10.1007/11508069_26},
  timestamp       = {20181201T1030}
}

@Article{lillicrap2015-continuous,
  author          = {Timothy P. Lillicrap and Jonathan J. Hunt and Alexander Pritzel and Nicolas Heess and Tom Erez and Yuval Tassa and
                  David Silver and Daan Wierstra},
  title           = {Continuous Control With Deep Reinforcement Learning},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1509.02971},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{lillicrap2016-random,
  author          = {Lillicrap, Timothy P and Cownden, Daniel and Tweed, Douglas B and Akerman, Colin J},
  title           = {Random Synaptic Feedback Weights Support Error Backpropagation for Deep Learning},
  journaltitle    = {Nature communications},
  year            = 2016,
  volume          = 7,
  journal         = {Nature communications},
  keywords        = {feedback alignment, random backprop},
  publisher       = {Nature Publishing Group},
  timestamp       = {20181201T1030}
}

@Report{lin1993-reinforcement,
  author          = {Lin, Long-Ji},
  title           = {Reinforcement learning for robots using neural networks},
  type            = {Tech report},
  institution     = {Carnegie-Mellon Univ Pittsburgh PA School of Computer Science},
  year            = 1993,
  keywords        = {rl, replay}
}

@Article{lin2013-network,
  author          = {Min Lin and Qiang Chen and Shuicheng Yan},
  title           = {Network in Network},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1312.4400},
  url             = {http://arxiv.org/abs/1312.4400},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LinCY13},
  keywords        = {nin, global max pooling, global average pooling},
  timestamp       = {20181201T1030}
}

@InProceedings{lin2014-microsoft,
  author          = {Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and
                  Doll{\'a}r, Piotr and Zitnick, C Lawrence},
  title           = {Microsoft coco: Common objects in context},
  year            = 2014,
  booktitle       = {European conference on computer vision},
  organization    = {Springer},
  pages           = {740--755},
  timestamp       = {20190130T1628}
}

@Article{lin2015-fixed,
  author          = {Darryl Dexu Lin and Sachin S. Talathi and V. Sreekanth Annapureddy},
  title           = {Fixed Point Quantization of Deep Convolutional Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06393},
  journal         = {CoRR},
  keywords        = {quantization, fixed point},
  timestamp       = {20181201T1030}
}

@Article{lin2015-neural,
  author          = {Zhouhan Lin and Matthieu Courbariaux and Roland Memisevic and Yoshua Bengio},
  title           = {Neural Networks With Few Multiplications},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1510.03009},
  url             = {http://arxiv.org/abs/1510.03009},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LinCMB15},
  keywords        = {quantization},
  timestamp       = {20181201T1030}
}

@InCollection{lin2017-runtime,
  author          = {Lin, Ji and Rao, Yongming and Lu, Jiwen and Zhou, Jie},
  title           = {Runtime Neural Pruning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2178--2188},
  url             = {http://papers.nips.cc/paper/6813-runtime-neural-pruning.pdf},
  keywords        = {pruning, markov, reinforcement, dynamic, q learning},
  timestamp       = {20181201T1030}
}

@Article{lin2017-structured,
  author          = {Zhouhan Lin and Minwei Feng and C{\'{\i}}cero Nogueira dos Santos and Mo Yu and Bing Xiang and Bowen Zhou and Yoshua
                  Bengio},
  title           = {A Structured Self-Attentive Sentence Embedding},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.03130},
  eprint          = {1703.03130},
  url             = {http://arxiv.org/abs/1703.03130},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/LinFSYXZB17},
  timestamp       = {20181201T1030}
}

@Article{lin2017-tactics,
  author          = {Lin, Yen-Chen and Hong, Zhang-Wei and Liao, Yuan-Hong and Shih, Meng-Li and Liu, Ming-Yu and Sun, Min},
  title           = {Tactics of Adversarial Attack on Deep Reinforcement Learning Agents},
  journaltitle    = {arXiv preprint arXiv:1703.06748},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1703.06748},
  keywords        = {adversarial, attack},
  timestamp       = {20181201T1030}
}

@Article{lin2017-why,
  author          = {{Lin}, Henry W. and {Tegmark}, Max and {Rolnick}, David},
  title           = {{Why Does Deep and Cheap Learning Work So Well?}},
  journaltitle    = {Journal of Statistical Physics},
  year            = 2017,
  volume          = 168,
  month           = sep,
  pages           = {1223-1247},
  doi             = {10.1007/s10955-017-1836-5},
  eprint          = {1608.08225},
  url             = {https://doi.org/10.1007/s10955-017-1836-5},
  journal         = {Journal of Statistical Physics},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017JSP...168.1223L},
  archiveprefix   = "arXiv",
  keywords        = {Artificial neural networks, Deep learning, Statistical physics},
  primaryclass    = "cond-mat.dis-nn",
  timestamp       = {20181216T1249}
}

@Article{ling2016-latent,
  author          = {Wang Ling and Edward Grefenstette and Karl Moritz Hermann and Tom{\'{a}}s Kocisk{\'{y}} and Andrew Senior and Fumin
                  Wang and Phil Blunsom},
  title           = {Latent Predictor Networks for Code Generation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.06744},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{liu2009-learning,
  author          = {Liu, Tie-Yan and others},
  title           = {Learning To Rank for Information Retrieval},
  journaltitle    = {Foundations and Trends{\textregistered} in Information Retrieval},
  year            = 2009,
  volume          = 3,
  number          = 3,
  pages           = {225--331},
  journal         = {Foundations and Trends{\textregistered} in Information Retrieval},
  keywords        = {learning to rank, survey},
  publisher       = {Now Publishers, Inc.},
  timestamp       = {20181201T1030}
}

@InProceedings{liu2015-learning,
  author          = {Liu, Pengfei and Qiu, Xipeng and Huang, Xuanjing},
  title           = {Learning Context-Sensitive Word Embeddings with Neural Tensor Skip-Gram Model.},
  year            = 2015,
  booktitle       = {IJCAI},
  pages           = {1284--1290},
  keywords        = {ntsg},
  timestamp       = {20181201T1030}
}

@InProceedings{liu2015-sparse,
  author          = {Liu, Baoyuan and Wang, Min and Foroosh, Hassan and Tappen, Marshall and Pensky, Marianna},
  title           = {Sparse convolutional neural networks},
  year            = 2015,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {806--814},
  keywords        = {pruning, saliency},
  timestamp       = {20181201T1030}
}

@Article{liu2015-ssd,
  author          = {Wei Liu and Dragomir Anguelov and Dumitru Erhan and Christian Szegedy and Scott E. Reed and Cheng{-}Yang Fu and
                  Alexander C. Berg},
  title           = {{SSD:} Single Shot Multibox Detector},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.02325},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InProceedings{liu2015-topical,
  author          = {Liu, Yang and Liu, Zhiyuan and Chua, Tat-Seng and Sun, Maosong},
  title           = {Topical Word Embeddings.},
  year            = 2015,
  booktitle       = {AAAI},
  pages           = {2418--2424},
  timestamp       = {20181201T1030}
}

@Article{liu2017-delving,
  author          = {Yanpei Liu and Xinyun Chen and Chang Liu and Dawn Song},
  title           = {Delving Into Transferable Adversarial Examples and Black-Box Attacks},
  keywords        = {adversarial, attack, ensemble, transfer},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1611.02770},
  url             = {http://arxiv.org/abs/1611.02770},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LiuCLS16},
  timestamp       = {20181201T1030}
}

@Article{liu2017-do,
  author          = {{Liu}, C. and {Bansal}, A. and {Fragoso}, V. and {Ramanan}, D.},
  title           = {{Do Convolutional Neural Networks Act As Compositional Nearest Neighbors?}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.10683},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171110683L},
  archiveprefix   = "arXiv",
  keywords        = {interpret, nearest neighbor, cnn, spatial prediction},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{liu2017-dynamic,
  author          = {Lanlan Liu and Jia Deng},
  title           = {Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-Offs By Selective Execution},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1701.00299},
  journal         = {CoRR},
  keywords        = {dynamic},
  timestamp       = {20181201T1030}
}

@Article{liu2017-hierarchical,
  author          = {{Liu}, H. and {Simonyan}, K. and {Vinyals}, O. and {Fernando}, C. and {Kavukcuoglu}, K.},
  title           = {{Hierarchical Representations for Efficient Architecture Search}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.00436},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171100436L},
  archiveprefix   = "arXiv",
  keywords        = {nas, evolution, architecture},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{liu2017-progressive,
  author          = {Liu, Chenxi and Zoph, Barret and Shlens, Jonathon and Hua, Wei and Li, Li-Jia and Fei-Fei, Li and Yuille, Alan and
                  Huang, Jonathan and Murphy, Kevin},
  title           = {Progressive Neural Architecture Search},
  journaltitle    = {arXiv preprint arXiv:1712.00559},
  year            = 2017,
  keywords        = {nas},
  journal         = {arXiv preprint arXiv:1712.00559}
}

@Article{liu2018-adversarial,
  author          = {{Liu}, H.-T.~D. and {Tao}, M. and {Li}, C.-L. and {Nowrouzezahrai}, D. and {Jacobson}, A.},
  title           = {{Adversarial Geometry and Lighting Using a Differentiable Renderer}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.02651},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180802651L},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack, 3d},
  timestamp       = {20181201T1030}
}

@Article{liu2018-beyond,
  author          = {Bei Liu and Jianlong Fu and Makoto P. Kato and Masatoshi Yoshikawa},
  title           = {Beyond Narrative Description: Generating Poetry From Images By Multi-Adversarial Training},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1804.08473},
  eprint          = {1804.08473},
  url             = {http://arxiv.org/abs/1804.08473},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1804-08473},
  timestamp       = {20181201T1030}
}

@Article{liu2018-darts,
  author          = {{Liu}, H. and {Simonyan}, K. and {Yang}, Y.},
  title           = {{DARTS: Differentiable Architecture Search}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jun,
  eprint          = {1806.09055},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180609055L},
  archiveprefix   = "arXiv",
  keywords        = {nas, darts},
  timestamp       = {20181201T1030}
}

@InProceedings{liu2018-hierarchical,
  author          = {Hanxiao Liu and Karen Simonyan and Oriol Vinyals and Chrisantha Fernando and Koray Kavukcuoglu},
  title           = {Hierarchical Representations for Efficient Architecture Search},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BJQRKzbA-},
  timestamp       = {20181201T1030}
}

@InProceedings{livni2014,
  author          = {Livni, Roi and Shalev-Shwartz, Shai and Shamir, Ohad},
  title           = {On the computational efficiency of training neural networks},
  year            = 2014,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {855--863},
  timestamp       = {20181201T1030}
}

@InProceedings{logeswaran2018-efficient,
  author          = {Lajanugen Logeswaran and Honglak Lee},
  title           = {An Efficient Framework for Learning Sentence Representations},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=rJvJXZb0W},
  timestamp       = {20181201T1030}
}

@Article{long2010-random,
  author          = {Long, Philip M and Servedio, Rocco A},
  title           = {Random Classification Noise Defeats All Convex Potential Boosters},
  journaltitle    = {Machine Learning},
  year            = 2010,
  volume          = 78,
  number          = 3,
  pages           = {287--304},
  journal         = {Machine Learning},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@InProceedings{long2015-fully,
  author          = {Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
  title           = {Fully Convolutional Networks for Semantic Segmentation},
  year            = 2015,
  booktitle       = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages           = {3431--3440},
  timestamp       = {20181201T1030}
}

@InCollection{long2017-learning,
  author          = {Long, Mingsheng and CAO, ZHANGJIE and Wang, Jianmin and Yu, Philip S},
  title           = {Learning Multiple Tasks with Multilinear Relationship Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1593--1602},
  url             = {http://papers.nips.cc/paper/6757-learning-multiple-tasks-with-multilinear-relationship-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{lopez2008-statistical,
  author          = {Lopez, Adam},
  title           = {Statistical Machine Translation},
  journaltitle    = {ACM Computing Surveys (CSUR)},
  year            = 2008,
  volume          = 40,
  number          = 3,
  pages           = 8,
  journal         = {ACM Computing Surveys (CSUR)},
  publisher       = {ACM},
  timestamp       = {20181201T1030}
}

@Article{louizos2016-structured,
  author          = {{Louizos}, C. and {Welling}, M.},
  title           = {{Structured and Efficient Variational Deep Learning With Matrix Gaussian Posteriors}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = mar,
  eprint          = {1603.04733},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InCollection{louizos2017-bayesian,
  author          = {Louizos, Christos and Ullrich, Karen and Welling, Max},
  title           = {Bayesian Compression for Deep Learning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3290--3300},
  url             = {http://papers.nips.cc/paper/6921-bayesian-compression-for-deep-learning.pdf},
  keywords        = {quantization, compression, node},
  timestamp       = {20181201T1030}
}

@InProceedings{louizos2017-multiplicative,
  author          = {Christos Louizos and Max Welling},
  title           = {Multiplicative Normalizing Flows for Variational {B}ayesian Neural Networks},
  year            = 2017,
  booktitle       = {Proceedings of the 34th International Conference on Machine Learning},
  editor          = {Doina Precup and Yee Whye Teh},
  volume          = 70,
  series          = {Proceedings of Machine Learning Research},
  publisher       = {PMLR},
  month           = {06--11 Aug},
  pages           = {2218--2227},
  url             = {http://proceedings.mlr.press/v70/louizos17a.html},
  address         = {International Convention Centre, Sydney, Australia},
  pdf             = {http://proceedings.mlr.press/v70/louizos17a/louizos17a.pdf},
  timestamp       = {20181209T1319}
}

@Article{louppe2016-learning,
  author          = {{Louppe}, G. and {Kagan}, M. and {Cranmer}, K.},
  title           = {{Learning To Pivot With Adversarial Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = nov,
  eprint          = {1611.01046},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing,
                  Physics - Data Analysis, Statistics and Probability, Statistics - Methodology},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{lowd2005-adversarial,
  author          = {Lowd, Daniel and Meek, Christopher},
  title           = {Adversarial learning},
  year            = 2005,
  booktitle       = {Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining},
  organization    = {ACM},
  pages           = {641--647},
  keywords        = {spam filter},
  timestamp       = {20181201T1030}
}

@InProceedings{lowd2005-good,
  author          = {Lowd, Daniel and Meek, Christopher},
  title           = {Good Word Attacks on Statistical Spam Filters.},
  year            = 2005,
  booktitle       = {CEAS},
  timestamp       = {20181201T1030}
}

@Article{lowe1988-multi,
  author          = {Lowe, D},
  title           = {Multi-Variable Functional Interpolation and Adaptive Networks},
  journaltitle    = {Complex Systems},
  year            = 1988,
  volume          = 2,
  pages           = {321--355},
  journal         = {Complex Systems},
  timestamp       = {20181201T1030}
}

@Article{lu2016-fully,
  author          = {Yongxi Lu and Abhishek Kumar and Shuangfei Zhai and Yu Cheng and Tara Javidi and Rog{\'{e}}rio Schmidt Feris},
  title           = {Fully-Adaptive Feature Sharing in Multi-Task Networks With Applications in Person Attribute Classification},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.05377},
  eprint          = {1611.05377},
  url             = {http://arxiv.org/abs/1611.05377},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/LuKZCJF16},
  keywords        = {multi-task},
  timestamp       = {20181201T1030}
}

@Article{lu2016-learning,
  author          = {Zhiyun Lu and Vikas Sindhwani and Tara N. Sainath},
  title           = {Learning Compact Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.02594},
  url             = {http://arxiv.org/abs/1604.02594},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LuSS16},
  timestamp       = {20181201T1030}
}

@InCollection{lu2017-expressive,
  author          = {Lu, Zhou and Pu, Hongming and Wang, Feicheng and Hu, Zhiqiang and Wang, Liwei},
  title           = {The Expressive Power of Neural Networks: A View from the Width},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6232--6240},
  url             = {http://papers.nips.cc/paper/7203-the-expressive-power-of-neural-networks-a-view-from-the-width.pdf},
  timestamp       = {20181201T1030}
}

@Article{lu2017-no,
  author          = {{Lu}, J. and {Sibai}, H. and {Fabry}, E. and {Forsyth}, D.},
  title           = {{NO Need To Worry About Adversarial Examples in Object Detection in Autonomous Vehicles}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.03501},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer
                  Science - Cryptography and Security},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{lu2017-safetynet,
  author          = {Lu, Jiajun and Issaranon, Theerasit and Forsyth, David},
  title           = {Safetynet: Detecting and Rejecting Adversarial Examples Robustly},
  journaltitle    = {arXiv preprint arXiv:1704.00103},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1704.00103},
  timestamp       = {20181201T1030}
}

@Article{lu2017-standard,
  author          = {{Lu}, J. and {Sibai}, H. and {Fabry}, E. and {Forsyth}, D.},
  title           = {{Standard Detectors Aren't (currently) Fooled By Physical Adversarial Stop signs}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.03337},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171003337L},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer
                  Science - Graphics},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{lucic2017-are,
  author          = {{Lucic}, M. and {Kurach}, K. and {Michalski}, M. and {Gelly}, S. and {Bousquet}, O.},
  title           = {{Are Gans Created Equal? a Large-Scale Study}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.10337},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171110337L},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{lukosevicius2009-reservoir,
  author          = "Mantas Luko{\v{s}}evi{\v{c}}ius and Herbert Jaeger",
  title           = {Reservoir Computing Approaches To Recurrent Neural Network Training},
  journaltitle    = {Computer Science Review},
  year            = 2009,
  volume          = 3,
  number          = 3,
  pages           = "127 - 149",
  issn            = "1574-0137",
  doi             = "https://doi.org/10.1016/j.cosrev.2009.03.005",
  url             = {https://doi.org/https://doi.org/10.1016/j.cosrev.2009.03.005},
  journal         = {Computer Science Review},
  keywords        = {reservoir, survey, echo state networks, liquid state machines, backpropagation decorrelation},
  timestamp       = {20181201T1030}
}

@Article{lukosevicius2009-survey,
  author          = {Luko{\vs}evi{\vc}ius, Mantas and Jaeger, Herbert},
  title           = {Survey: Reservoir Computing Approaches To Recurrent Neural Network Training},
  journaltitle    = {Comput. Sci. Rev.},
  year            = 2009,
  volume          = 3,
  number          = 3,
  month           = aug,
  pages           = {127--149},
  issn            = {1574-0137},
  doi             = {10.1016/j.cosrev.2009.03.005},
  url             = {https://doi.org/10.1016/j.cosrev.2009.03.005},
  journal         = {Comput. Sci. Rev.},
  acmid           = 2296036,
  address         = {Amsterdam, The Netherlands, The Netherlands},
  issue_date      = {August, 2009},
  numpages        = 23,
  publisher       = {Elsevier Science Publishers B. V.},
  timestamp       = {20181201T1030}
}

@Article{lundberg2016-unexpected,
  author          = {Scott Lundberg and Su{-}In Lee},
  title           = {An Unexpected Unity Among Methods for Interpreting Model Predictions},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.07478},
  eprint          = {1611.07478},
  url             = {http://arxiv.org/abs/1611.07478},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/LundbergL16},
  keywords        = {interpret},
  timestamp       = {20181201T1030}
}

@Article{luo2015-foveation,
  author          = {Yan Luo and Xavier Boix and Gemma Roig and Tomaso A. Poggio and Qi Zhao},
  title           = {Foveation-Based Mechanisms Alleviate Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06292},
  url             = {http://arxiv.org/abs/1511.06292},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LuoBRPZ15},
  keywords        = {adversarial},
  timestamp       = {20181201T1030}
}

@Article{luo2016-learning,
  author          = {{Luo}, Y. and {Chiu}, C.-C. and {Jaitly}, N. and {Sutskever}, I.},
  title           = {{Learning Online Alignments With Continuous Rewards Policy Gradient}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = aug,
  eprint          = {1608.01281},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Computation and Language},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InCollection{luo2017-label,
  author          = {Luo, Zelun and Zou, Yuliang and Hoffman, Judy and Fei-Fei, Li F},
  title           = {Label Efficient Learning of Transferable Representations acrosss Domains and Tasks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {164--176},
  url             = {http://papers.nips.cc/paper/6621-label-efficient-learning-of-transferable-representations-acrosss-domains-and-tasks.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{luong2013-better,
  author          = {Luong, Thang and Socher, Richard and Manning, Christopher},
  title           = {Better word representations with recursive neural networks for morphology},
  year            = 2013,
  booktitle       = {Proceedings of the Seventeenth Conference on Computational Natural Language Learning},
  pages           = {104--113},
  timestamp       = {20181201T1030}
}

@Article{luong2014-addressing,
  author          = {Thang Luong and Ilya Sutskever and Quoc V. Le and Oriol Vinyals and Wojciech Zaremba},
  title           = {Addressing the Rare Word Problem in Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1410.8206},
  url             = {http://arxiv.org/abs/1410.8206},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LuongSLVZ14},
  timestamp       = {20181201T1030}
}

@Article{luong2015-effective,
  author          = {Luong, Minh-Thang and Pham, Hieu and Manning, Christopher D},
  title           = {Effective Approaches To Attention-Based Neural Machine Translation},
  journaltitle    = {arXiv preprint arXiv:1508.04025},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1508.04025},
  timestamp       = {20181201T1030}
}

@Article{luong2016-achieving,
  author          = {Minh{-}Thang Luong and Christopher D. Manning},
  title           = {Achieving Open Vocabulary Neural Machine Translation With Hybrid Word-Character Models},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.00788},
  url             = {http://arxiv.org/abs/1604.00788},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/LuongM16},
  timestamp       = {20181201T1030}
}

@Unpublished{luong2016-neural,
  author          = {Luong, Thang and Cho, Kyunghyun and Manning, Christopher},
  title           = {Neural Machine Translation},
  year            = 2016,
  note            = {ACL 2016},
  timestamp       = {20181201T1030}
}

@InCollection{ma2017-diving,
  author          = {Ma, Siyuan and Belkin, Mikhail},
  title           = {Diving into the shallows: a computational perspective on large-scale shallow learning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3781--3790},
  url             = {http://papers.nips.cc/paper/6968-diving-into-the-shallows-a-computational-perspective-on-large-scale-shallow-learning.pdf},
  timestamp       = {20181201T1030}
}

@Article{ma2018-universal,
  author          = {Ma, Chen and Wen, Junfeng and Bengio, Yoshua},
  title           = {Universal Successor Representations for Transfer Reinforcement Learning},
  journaltitle    = {ICLR Review},
  year            = 2018,
  journal         = {ICLR Review},
  timestamp       = {20181201T1030}
}

@InProceedings{maas2011-learning,
  author          = {Maas, Andrew L.  and Daly, Raymond E.  and Pham, Peter T.  and Huang, Dan and Ng, Andrew Y.  and Potts, Christopher},
  title           = {Learning Word Vectors for Sentiment Analysis},
  year            = 2011,
  booktitle       = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  publisher       = {Association for Computational Linguistics},
  month           = {June},
  pages           = {142--150},
  url             = {http://www.aclweb.org/anthology/P11-1015},
  address         = {Portland, Oregon, USA},
  keywords        = {data, imdb},
  timestamp       = {20181201T1030}
}

@InCollection{maass1994-boolean,
  author          = {Maass, Wolfgang and Schnitger, Georg and Sontag, Eduardo D},
  title           = {A comparison of the computational power of sigmoid and Boolean threshold circuits},
  year            = 1994,
  booktitle       = {Theoretical Advances in Neural Computation and Learning},
  publisher       = {Springer},
  pages           = {127--151},
  timestamp       = {20181201T1030}
}

@Article{maass2002-fresh,
  author          = {Maass, Wolfgang and Natschl{\"a}ger, T and Markram, Henry},
  title           = {A Fresh Look At Real-Time Computation in Generic Recurrent Neural Circuits},
  journaltitle    = {Institute for Theoretical Computer Science, TU Graz, Graz, Austria},
  year            = 2002,
  journal         = {Institute for Theoretical Computer Science, TU Graz, Graz, Austria},
  timestamp       = {20181201T1030}
}

@Article{maass2002-real,
  author          = {Maass, Wolfgang and Natschl{\"a}ger, Thomas and Markram, Henry},
  title           = {Real-Time Computing Without Stable States: a New Framework for Neural Computation Based on Perturbations},
  journaltitle    = {Neural Comput.},
  year            = 2002,
  volume          = 14,
  number          = 11,
  month           = nov,
  pages           = {2531--2560},
  issn            = {0899-7667},
  doi             = {10.1162/089976602760407955},
  url             = {https://doi.org/10.1162/089976602760407955},
  journal         = {Neural Comput.},
  acmid           = 639718,
  address         = {Cambridge, MA, USA},
  issue_date      = {November 2002},
  keywords        = {liquid state machine},
  numpages        = 30,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{maaten2008-visualizing,
  author          = {L.J.P van der Maaten and G.E. Hinton},
  title           = {Visualizing High-Dimensional Data Using T-Sne},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2008,
  volume          = {9: 2579-2605},
  url             = {http://arxiv.org/abs/1207.0580},
  journal         = {Journal of Machine Learning Research},
  bibsource       = {DBLP, http://dblp.uni-trier.de},
  timestamp       = {20181201T1030}
}

@Article{maaten2012-visualizing,
  author          = {Maaten, Laurens and Hinton, Geoffrey},
  title           = {Visualizing Non-Metric Similarities in Multiple Maps},
  journaltitle    = {Mach. Learn.},
  year            = 2012,
  volume          = 87,
  number          = 1,
  month           = apr,
  pages           = {33--55},
  issn            = {0885-6125},
  doi             = {10.1007/s10994-011-5273-4},
  url             = {https://doi.org/10.1007/s10994-011-5273-4},
  journal         = {Mach. Learn.},
  acmid           = 2198172,
  address         = {Hingham, MA, USA},
  issue_date      = {April 2012},
  keywords        = {Data visualization, Embedding, Multidimensional scaling, Non-metric similarities},
  numpages        = 23,
  publisher       = {Kluwer Academic Publishers},
  timestamp       = {20181201T1030}
}

@Article{machado2015-computational,
  author          = {Machado, Emerson Lopes and Miosso, Cristiano Jacques and von Borries, Ricardo and Coutinho, Murilo and Berger, Pedro de
                  Azevedo and Marques, Thiago and Jacobi, Ricardo Pezzuol},
  title           = {Computational Cost Reduction in Learned Transform Classifications},
  journaltitle    = {arXiv preprint arXiv:1504.06779},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1504.06779},
  keywords        = {quantization, fpga},
  timestamp       = {20181201T1030}
}

@Article{mackay1995-probable,
  author          = {MacKay, David JC},
  title           = {Probable Networks and Plausible Predictions-A Review of Practical Bayesian Methods for Supervised Neural Networks},
  journaltitle    = {Network: Computation in Neural Systems},
  year            = 1995,
  volume          = 6,
  number          = 3,
  pages           = {469--505},
  journal         = {Network: Computation in Neural Systems},
  keywords        = {pruning, bayesian},
  publisher       = {Taylor \& Francis},
  timestamp       = {20181201T1030}
}

@Book{mackay2003-information,
  author          = {MacKay, David JC},
  title           = {Information theory, inference and learning algorithms},
  year            = 2003,
  publisher       = {Cambridge university press},
  timestamp       = {20181201T1030}
}

@Article{maddison2016-concrete,
  author          = {Chris J. Maddison and Andriy Mnih and Yee Whye Teh},
  title           = {The Concrete Distribution: {A} Continuous Relaxation of Discrete Random Variables},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.00712},
  url             = {http://arxiv.org/abs/1611.00712},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MaddisonMT16},
  keywords        = {gumbel, discrete},
  timestamp       = {20181201T1030}
}

@Article{madry2017-towards,
  author          = {Madry, Aleksander and Makelov, Aleksandar and Schmidt, Ludwig and Tsipras, Dimitris and Vladu, Adrian},
  title           = {Towards Deep Learning Models Resistant To Adversarial Attacks},
  journaltitle    = {arXiv preprint arXiv:1706.06083},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.06083},
  keywords        = {adversarial, hypothesis, defense, pgd},
  timestamp       = {20181201T1030}
}

@Article{mahendran2014-understanding,
  author          = {Aravindh Mahendran and Andrea Vedaldi},
  title           = {Understanding Deep Image Representations By Inverting Them},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.0035},
  url             = {http://arxiv.org/abs/1412.0035},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MahendranV14},
  keywords        = {intrepret, cnn},
  timestamp       = {20181201T1030}
}

@InCollection{mahsereci2015-probabilistic,
  author          = {Mahsereci, Maren and Hennig, Philipp},
  title           = {Probabilistic Line Searches for Stochastic Optimization},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {181--189},
  url             = {http://papers.nips.cc/paper/5753-probabilistic-line-searches-for-stochastic-optimization.pdf},
  timestamp       = {20181201T1030}
}

@Article{makhzani2013-k,
  author          = {Alireza Makhzani and Brendan J. Frey},
  title           = {K-Sparse Autoencoders},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1312.5663},
  url             = {http://arxiv.org/abs/1312.5663},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MakhzaniF13},
  timestamp       = {20181201T1030}
}

@InCollection{makhzani2015-winner,
  author          = {Makhzani, Alireza and Frey, Brendan J},
  title           = {Winner-Take-All Autoencoders},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2791--2799},
  url             = {http://papers.nips.cc/paper/5783-winner-take-all-autoencoders.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{mandischer1993-representation,
  author          = {Mandischer, Martin},
  title           = {Representation and evolution of neural networks},
  year            = 1993,
  booktitle       = {Artificial Neural Nets and Genetic Algorithms},
  organization    = {Springer},
  pages           = {643--649},
  timestamp       = {20181201T1030}
}

@InProceedings{manning2014-stanford,
  author          = {Manning, Christopher and Surdeanu, Mihai and Bauer, John and Finkel, Jenny and Bethard, Steven and McClosky, David},
  title           = {The Stanford CoreNLP natural language processing toolkit},
  year            = 2014,
  booktitle       = {Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations},
  pages           = {55--60},
  timestamp       = {20181201T1030}
}

@Article{marblestone2016-toward,
  author          = {Marblestone, Adam H and Wayne, Greg and Kording, Konrad P},
  title           = {Toward an Integration of Deep Learning and Neuroscience},
  journaltitle    = {Frontiers in computational neuroscience},
  year            = 2016,
  volume          = 10,
  journal         = {Frontiers in computational neuroscience},
  publisher       = {Frontiers Media SA},
  timestamp       = {20181201T1030}
}

@Article{marchesi1993-fast,
  author          = {Marchesi, Michele and Orlandi, Gianni and Piazza, Francesco and Uncini, Aurelio},
  title           = {Fast Neural Networks Without Multipliers},
  journaltitle    = {IEEE transactions on Neural Networks},
  year            = 1993,
  volume          = 4,
  number          = 1,
  pages           = {53--62},
  journal         = {IEEE transactions on Neural Networks},
  keywords        = {quantization},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{marcus1993-building,
  author          = {Marcus, Mitchell P and Marcinkiewicz, Mary Ann and Santorini, Beatrice},
  title           = {Building a Large Annotated Corpus of English: the Penn Treebank},
  journaltitle    = {Computational linguistics},
  year            = 1993,
  volume          = 19,
  number          = 2,
  pages           = {313--330},
  journal         = {Computational linguistics},
  keywords        = {data, ptb},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{marcus2018-deep,
  author          = {{Marcus}, G.},
  title           = {{Deep Learning: a Critical Appraisal}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.00631},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180100631M},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Learning, Statistics - Machine Learning, 97R40, I.2.0,
                  I.2.6},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@Article{marcus2018-innateness,
  author          = {{Marcus}, G.},
  title           = {{Innateness, Alphazero, and Artificial Intelligence}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.05667},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180105667M},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, 97R40, I.2.0, I.2.6},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@InProceedings{marelli2014-semeval,
  author          = {Marelli, Marco and Bentivogli, Luisa and Baroni, Marco and Bernardi, Raffaella and Menini, Stefano and Zamparelli,
                  Roberto},
  title           = {Semeval-2014 task 1: Evaluation of compositional distributional semantic models on full sentences through semantic
                  relatedness and textual entailment},
  year            = 2014,
  booktitle       = {Proceedings of the 8th international workshop on semantic evaluation (SemEval 2014)},
  pages           = {1--8},
  keywords        = {sick},
  timestamp       = {20181201T1030}
}

@InProceedings{marelli2014-sick,
  author          = {Marelli, Marco and Menini, Stefano and Baroni, Marco and Bentivogli, Luisa and Bernardi, Raffaella and Zamparelli,
                  Roberto and others},
  title           = {A SICK Cure for the Evaluation of Compositional Distributional Semantic Models.},
  keywords        = {data, sick},
  year            = 2014,
  booktitle       = {LREC},
  pages           = {216--223},
  timestamp       = {20181230T1048}
}

@Article{marino2016-more,
  author          = {{Marino}, K. and {Salakhutdinov}, R. and {Gupta}, A.},
  title           = {{The More You Know: Using Knowledge Graphs for Image Classification}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = dec,
  eprint          = {1612.04844},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{markram2012-spike,
  author          = {Markram, Henry and Gerstner, Wulfram and Sj{\"o}str{\"o}m, Per Jesper},
  title           = {Spike-Timing-Dependent Plasticity: a Comprehensive Overview},
  journaltitle    = {Frontiers in synaptic neuroscience},
  year            = 2012,
  volume          = 4,
  journal         = {Frontiers in synaptic neuroscience},
  publisher       = {Frontiers Media SA},
  timestamp       = {20181201T1030}
}

@Article{martens2015-optimizing,
  author          = {James Martens and Roger B. Grosse},
  title           = {Optimizing Neural Networks With Kronecker-Factored Approximate Curvature},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1503.05671},
  journal         = {CoRR},
  keywords        = {k-fac},
  timestamp       = {20181201T1030}
}

@InProceedings{marti1992-genetically,
  author          = {Marti, Leonardo},
  title           = {Genetically generated neural networks. II. Searching for an optimal representation},
  year            = 1992,
  booktitle       = {Neural Networks, 1992. IJCNN., International Joint Conference on},
  volume          = 2,
  organization    = {IEEE},
  pages           = {221--226},
  timestamp       = {20181201T1030}
}

@Article{martin2017-rethinking,
  author          = {Charles H. Martin and Michael W. Mahoney},
  title           = {Rethinking Generalization Requires Revisiting Old Ideas: Statistical Mechanics Approaches and Complex Learning
                  Behavior},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1710.09553},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{mathias1996-empirical,
  author          = {Mathias, Keith and Whitley, Darrell and Kusuma, Anthony and Stork, Christof},
  title           = {An Empirical Evaluation of Genetic Algorithms on Noisy Objective Functions},
  journaltitle    = {Genetic algorithms for pattern recognition},
  year            = 1996,
  pages           = {65--86},
  journal         = {Genetic algorithms for pattern recognition},
  timestamp       = {20181201T1030}
}

@InProceedings{mathieu2016-disentangling,
  author          = {Mathieu, Michael F and Zhao, Junbo Jake and Zhao, Junbo and Ramesh, Aditya and Sprechmann, Pablo and LeCun, Yann},
  title           = {Disentangling factors of variation in deep representation using adversarial training},
  keywords        = {disentangle},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {5041--5049},
  timestamp       = {20181201T1030}
}

@Thesis{matthews2016-scalable,
  author          = {Matthews, A},
  title           = {Scalable Gaussian process inference using variational methods},
  type            = {PhD thesis},
  institution     = {University of Cambridge},
  year            = 2016,
  timestamp       = {20181201T1030}
}

@InProceedings{matthews2016-synthesizing,
  author          = {Austin Matthews and Eva Schlinger and Alon Lavie and Chris Dyer},
  title           = {Synthesizing Compound Words for Machine Translation},
  year            = 2016,
  booktitle       = {{ACL} {(1)}},
  publisher       = {The Association for Computer Linguistics},
  timestamp       = {20181201T1030}
}

@InProceedings{mauro2012-wit3,
  author          = {Mauro, Cettolo and Christian, Girardi and Marcello, Federico},
  title           = {Wit3: Web inventory of transcribed and translated talks},
  year            = 2012,
  booktitle       = {Conference of European Association for Machine Translation},
  pages           = {261--268},
  timestamp       = {20181201T1030}
}

@InCollection{mazumdar2015-associative,
  author          = {Mazumdar, Arya and Rawat, Ankit Singh},
  title           = {Associative Memory via a Sparse Recovery Model},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2701--2709},
  url             = {http://papers.nips.cc/paper/5915-associative-memory-via-a-sparse-recovery-model.pdf},
  timestamp       = {20181201T1030}
}

@Article{mcaleer2018-solving,
  author          = {Stephen McAleer and Forest Agostinelli and Alexander Shmakov and Pierre Baldi},
  title           = {Solving the Rubik's Cube Without Human Knowledge},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1805.07470},
  eprint          = {1805.07470},
  url             = {http://arxiv.org/abs/1805.07470},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1805-07470},
  timestamp       = {20190203T1649}
}

@InProceedings{mcauley2015-inferring,
  author          = {McAuley, Julian and Pandey, Rahul and Leskovec, Jure},
  title           = {Inferring networks of substitutable and complementary products},
  year            = 2015,
  booktitle       = {Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  organization    = {ACM},
  pages           = {785--794},
  keywords        = {data, amazon product catelog},
  timestamp       = {20181201T1030}
}

@InCollection{mccann2017-learned,
  author          = {McCann, Bryan and Bradbury, James and Xiong, Caiming and Socher, Richard},
  title           = {Learned in Translation: Contextualized Word Vectors},
  keywords        = {embedding, word, cove},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6297--6308},
  url             = {http://papers.nips.cc/paper/7209-learned-in-translation-contextualized-word-vectors.pdf},
  timestamp       = {20181201T1030}
}

@Article{mccusker1981-word,
  author          = {McCusker, Leo X and Gough, Philip B and Bias, Randolph G},
  title           = {Word Recognition Inside Out and Outside In.},
  keywords        = {brain, linguistic, psycho},
  journaltitle    = {Journal of Experimental Psychology: Human Perception and Performance},
  year            = 1981,
  volume          = 7,
  number          = 3,
  pages           = 538,
  journal         = {Journal of Experimental Psychology: Human Perception and Performance},
  publisher       = {American Psychological Association},
  timestamp       = {20190106T1048}
}

@InProceedings{mcmahan2013-ad,
  author          = {H. Brendan McMahan and Gary Holt and D. Sculley and Michael Young and Dietmar Ebner and Julian Grady and Lan Nie and
                  Todd Phillips and Eugene Davydov and Daniel Golovin and Sharat Chikkerur and Dan Liu and Martin Wattenberg and Arnar Mar
                  Hrafnkelsson and Tom Boulos and Jeremy Kubica},
  title           = {Ad Click Prediction: a View from the Trenches},
  year            = 2013,
  booktitle       = {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
  timestamp       = {20181201T1030}
}

@InProceedings{mcmahan2016-communication,
  author          = {H. Brendan McMahan and Eider Moore and Daniel Ramage and Seth Hampson and Blaise Aguera y Arcas},
  title           = {Communication-Efficient Learning of Deep Networks from Decentralized Data},
  year            = 2016,
  booktitle       = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  url             = {http://arxiv.org/abs/1602.05629},
  timestamp       = {20181201T1030}
}

@Article{melis2017-state,
  author          = {G{\'{a}}bor Melis and Chris Dyer and Phil Blunsom},
  title           = {On the State of the Art of Evaluation in Neural Language Models},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.05589},
  eprint          = {1707.05589},
  url             = {http://arxiv.org/abs/1707.05589},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/MelisDB17},
  timestamp       = {20181201T1030}
}

@Article{mellempudi2017-ternary,
  author          = {Naveen Mellempudi and Abhisek Kundu and Dheevatsa Mudigere and Dipankar Das and Bharat Kaul and Pradeep Dubey},
  title           = {Ternary Neural Networks With Fine-Grained Quantization},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1705.01462},
  journal         = {CoRR},
  keywords        = {quantization, ternary},
  timestamp       = {20181201T1030}
}

@Article{meng2017-magnet,
  author          = {Meng, Dongyu and Chen, Hao},
  title           = {Magnet: a Two-Pronged Defense Against Adversarial Examples},
  journaltitle    = {arXiv preprint arXiv:1705.09064},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.09064},
  keywords        = {adversarial, defense, autoencoder},
  timestamp       = {20181201T1030}
}

@Article{meng2018-g,
  author          = {{Meng}, Qi and {Zheng}, Shuxin and {Zhang}, Huishuai and {Chen}, Wei and {Ma}, Zhi-Ming and {Liu}, Tie-Yan},
  title           = {{\$\textbackslashmathcal\{G\}\$-SGD: Optimizing Relu Neural Networks in Its Positively Scale-Invariant Space}},
  journaltitle    = {arXiv e-prints},
  year            = 2018,
  eid             = {arXiv:1802.03713},
  month           = Feb,
  pages           = {arXiv:1802.03713},
  eprint          = {1802.03713},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/\#abs/2018arXiv180203713M},
  archiveprefix   = {arXiv},
  keywords        = {Statistics - Machine Learning, Computer Science - Machine Learning},
  primaryclass    = {stat.ML},
  timestamp       = {20190107T1424}
}

@Article{merity2016-pointer,
  author          = {Merity, Stephen and Xiong, Caiming and Bradbury, James and Socher, Richard},
  title           = {Pointer Sentinel Mixture Models},
  journaltitle    = {arXiv preprint arXiv:1609.07843},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1609.07843},
  keywords        = {data, wikitext},
  timestamp       = {20181201T1030}
}

@InProceedings{merity2018-regularizing,
  author          = {Stephen Merity and Nitish Shirish Keskar and Richard Socher},
  title           = {Regularizing and Optimizing {LSTM} Language Models},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SyyGPP0TZ},
  timestamp       = {20181201T1030}
}

@Article{merolla2016-deep,
  author          = {Paul Merolla and Rathinakumar Appuswamy and John V. Arthur and Steven K. Esser and Dharmendra S. Modha},
  title           = {Deep Neural Networks Are Robust To Weight Binarization and Other Non-Linear Distortions},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.01981},
  journal         = {CoRR},
  keywords        = {quantization, binary},
  timestamp       = {20181201T1030}
}

@Article{mesnard2016-towards,
  author          = {{Mesnard}, T. and {Gerstner}, W. and {Brea}, J.},
  title           = {{Towards Deep Learning With Spiking Neurons in Energy Based Models With Contrastive Hebbian plasticity}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = dec,
  eprint          = {1612.03214},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{mesnard2018-fully,
  author          = {Mesnard, Thomas and Vignoud, Ga{\"e}tan and Binas, Jonathan and Bengio, Yoshua},
  title           = {Fully Discretized Training of Neural Networks Through Direct Feedback},
  journaltitle    = {openreview},
  year            = 2018,
  timestamp       = {20181201T1030}
}

@Article{metzen2017-detecting,
  author          = {Metzen, Jan Hendrik and Genewein, Tim and Fischer, Volker and Bischoff, Bastian},
  title           = {On Detecting Adversarial Perturbations},
  journaltitle    = {arXiv preprint arXiv:1702.04267},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.04267},
  keywords        = {adversarial, defense},
  timestamp       = {20181201T1030}
}

@Article{metzen2017-universal,
  author          = {Metzen, Jan Hendrik and Kumar, Mummadi Chaithanya and Brox, Thomas and Fischer, Volker},
  title           = {Universal Adversarial Perturbations Against Semantic Image Segmentation},
  journaltitle    = {arXiv preprint arXiv:1704.05712},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1704.05712},
  timestamp       = {20181201T1030}
}

@Article{mezard1985-replicas,
  author          = {M{\'e}zard, Marc and Parisi, Giorgio},
  title           = {Replicas and Optimization},
  journaltitle    = {Journal de Physique Lettres},
  year            = 1985,
  volume          = 46,
  number          = 17,
  pages           = {771--778},
  journal         = {Journal de Physique Lettres},
  publisher       = {Les Editions de Physique},
  timestamp       = {20181201T1030}
}

@Article{mezard2002-analytic,
  author          = {M{\'e}zard, Marc and Parisi, Giorgio and Zecchina, Riccardo},
  title           = {Analytic and Algorithmic Solution of Random Satisfiability Problems},
  journaltitle    = {Science},
  year            = 2002,
  volume          = 297,
  number          = 5582,
  pages           = {812--815},
  journal         = {Science},
  publisher       = {American Association for the Advancement of Science},
  timestamp       = {20181201T1030}
}

@Misc{mezard2009-information,
  author          = {M{\'e}zard, Marc and Montanari, Andrea},
  title           = {Information, physics, and computation},
  year            = 2009,
  publisher       = {Oxford Graduate Texts (Oxford University Press, Oxford, 2009)},
  timestamp       = {20181201T1030}
}

@Article{miikkulainen2017-evolving,
  author          = {{Miikkulainen}, R. and {Liang}, J. and {Meyerson}, E. and {Rawal}, A. and {Fink}, D. and {Francon}, O. and {Raju},
                  B. and {Shahrzad}, H. and {Navruzyan}, A. and {Duffy}, N. and {Hodjat}, B.},
  title           = {{Evolving Deep Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.00548},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {evolution, genetic, CoDeepNEAT},
  timestamp       = {20181201T1030}
}

@Article{mikolov2013-distributed,
  author          = {Tomas Mikolov and Ilya Sutskever and Kai Chen and Greg Corrado and Jeffrey Dean},
  title           = {Distributed Representations of Words and Phrases and Their Compositionality},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1310.4546},
  url             = {http://arxiv.org/abs/1310.4546},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MikolovSCCD13},
  keywords        = {embedding, text, word2vec},
  timestamp       = {20181201T1030}
}

@Article{mikolov2013-efficient,
  author          = {Tomas Mikolov and Kai Chen and Greg Corrado and Jeffrey Dean},
  title           = {Efficient Estimation of Word Representations in Vector Space},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1301.3781},
  url             = {http://arxiv.org/abs/1301.3781},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1301-3781},
  keywords        = {embedding, word, word2vec, skip-gram, cbow},
  timestamp       = {20181201T1030}
}

@InProceedings{mikolov2013-linguistic,
  author          = {Mikolov, Tomas and Yih, Wen-tau and Zweig, Geoffrey},
  title           = {Linguistic regularities in continuous space word representations.},
  year            = 2013,
  booktitle       = {hlt-Naacl},
  volume          = 13,
  pages           = {746--751},
  keywords        = {embedding, word},
  timestamp       = {20181201T1030}
}

@Article{mikolov2014-learning,
  author          = {Mikolov, Tomas and Joulin, Armand and Chopra, Sumit and Mathieu, Michael and Ranzato, Marc'Aurelio},
  title           = {Learning Longer Memory in Recurrent Neural Networks},
  journaltitle    = {arXiv preprint arXiv:1412.7753},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1412.7753},
  keywords        = {data, text8},
  timestamp       = {20181201T1030}
}

@Article{mikolov2017-advances,
  author          = {{Mikolov}, T. and {Grave}, E. and {Bojanowski}, P. and {Puhrsch}, C. and {Joulin}, A.},
  title           = {{Advances in Pre-Training Distributed Word Representations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.09405},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171209405M},
  archiveprefix   = "arXiv",
  keywords        = {word2vec},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{miller1989-designing,
  author          = {Miller, Geoffrey F. and Todd, Peter M. and Hegde, Shailesh U.},
  title           = {Designing Neural Networks Using Genetic Algorithms},
  year            = 1989,
  booktitle       = {Proceedings of the Third International Conference on Genetic Algorithms},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  location        = {George Mason University, USA},
  isbn            = {1-55860-006-3},
  pages           = {379--384},
  url             = {http://dl.acm.org/citation.cfm?id=93126.94034},
  acmid           = 94034,
  address         = {San Francisco, CA, USA},
  numpages        = 6,
  timestamp       = {20181201T1030}
}

@Article{miller1991-contextual,
  author          = {Miller, George A and Charles, Walter G},
  title           = {Contextual Correlates of Semantic Similarity},
  journaltitle    = {Language and cognitive processes},
  year            = 1991,
  volume          = 6,
  number          = 1,
  pages           = {1--28},
  journal         = {Language and cognitive processes},
  keywords        = {mc},
  publisher       = {Taylor \& Francis},
  timestamp       = {20181201T1030}
}

@InProceedings{miller1997-mixture,
  author          = {Miller, David J and Uyar, Hasan S},
  title           = {A Mixture of Experts Classifier with Learning Based on Both Labelled and Unlabelled Data},
  year            = 1997,
  booktitle       = {Advances in neural information processing systems},
  pages           = {571--577},
  timestamp       = {20181201T1030}
}

@Article{miller2018-when,
  author          = {John Miller and Moritz Hardt},
  title           = {When Recurrent Models Don't Need To Be Recurrent},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1805.10369},
  eprint          = {1805.10369},
  url             = {http://arxiv.org/abs/1805.10369},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1805-10369},
  timestamp       = {20190109T1357}
}

@Article{mills2017-deep,
  author          = {{Mills}, K. and {Spanner}, M. and {Tamblyn}, I.},
  title           = {{Deep Learning and the Schr$\backslash$``odinger equation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.01361},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Condensed Matter - Materials Science, Computer Science - Learning, Physics - Chemical Physics},
  primaryclass    = "cond-mat.mtrl-sci",
  timestamp       = {20181201T1030}
}

@Article{minsky1961-steps,
  author          = {Minsky, Marvin},
  title           = {Steps Toward Artificial Intelligence},
  journaltitle    = {Proceedings of the IRE},
  year            = 1961,
  volume          = 49,
  number          = 1,
  pages           = {8--30},
  journal         = {Proceedings of the IRE},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{mirza2014-conditional,
  author          = {Mehdi Mirza and Simon Osindero},
  title           = {Conditional Generative Adversarial Nets},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1411.1784},
  url             = {http://arxiv.org/abs/1411.1784},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{mishkin2016-systematic,
  author          = {{Mishkin}, D. and {Sergievskiy}, N. and {Matas}, J.},
  title           = {{Systematic Evaluation of Cnn Advances on the ImageNet}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.02228},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Neural and Evolutionary Computing, Computer Science - Computer Vision and Pattern Recognition,
                  Computer Science - Learning},
  timestamp       = {20181201T1030}
}

@Article{mishra2017-meta,
  author          = {{Mishra}, N. and {Rohaninejad}, M. and {Chen}, X. and {Abbeel}, P.},
  title           = {{Meta-Learning With Temporal Convolutions}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.03141},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Learning, Computer Science - Neural and Evolutionary
                  Computing, Statistics - Machine Learning},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@InProceedings{mishra2018-wrpn,
  author          = {Asit Mishra and Eriko Nurvitadhi and Jeffrey J Cook and Debbie Marr},
  title           = {{WRPN}: Wide Reduced-Precision Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=B1ZvaaeAZ},
  timestamp       = {20181201T1030}
}

@Article{misra2017-modification,
  author          = {Rajesh Misra and Kumar S. Ray},
  title           = {A Modification of Particle Swarm Optimization Using Random Walk},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.10401},
  journal         = {CoRR},
  keywords        = {pso},
  timestamp       = {20181201T1030}
}

@Article{mitchell2008-predicting,
  author          = {Mitchell, Tom M and Shinkareva, Svetlana V and Carlson, Andrew and Chang, Kai-Min and Malave, Vicente L and Mason,
                  Robert A and Just, Marcel Adam},
  title           = {Predicting Human Brain Activity Associated With the Meanings of Nouns},
  journaltitle    = {science},
  year            = 2008,
  volume          = 320,
  number          = 5880,
  pages           = {1191--1195},
  journal         = {science},
  publisher       = {American Association for the Advancement of Science},
  timestamp       = {20181201T1030}
}

@Article{mitra2017-neural,
  author          = {Bhaskar Mitra and Nick Craswell},
  title           = {Neural Models for Information Retrieval},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1705.01509},
  eprint          = {1705.01509},
  url             = {http://arxiv.org/abs/1705.01509},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/MitraC17},
  keywords        = {information retrieval},
  timestamp       = {20181201T1030}
}

@Article{miyashita2016-convolutional,
  author          = {Daisuke Miyashita and Edward H. Lee and Boris Murmann},
  title           = {Convolutional Neural Networks Using Logarithmic Data Representation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.01025},
  url             = {http://arxiv.org/abs/1603.01025},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MiyashitaLM16},
  keywords        = {quantization, log, cnn, imagenet},
  timestamp       = {20181201T1030}
}

@Article{miyato2015-distributional,
  author          = {Miyato, Takeru and Maeda, Shin-ichi and Koyama, Masanori and Nakae, Ken and Ishii, Shin},
  title           = {Distributional Smoothing With Virtual Adversarial Training},
  journaltitle    = {stat},
  year            = 2015,
  volume          = 1050,
  pages           = 25,
  journal         = {stat},
  keywords        = {adversarial, attack, vatm, fgvm},
  timestamp       = {20181201T1030}
}

@Article{miyato2016-adversarial,
  author          = {{Miyato}, T. and {Dai}, A.~M. and {Goodfellow}, I.},
  title           = {{Adversarial Training Methods for Semi-Supervised Text Classification}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = may,
  eprint          = {1605.07725},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2016arXiv160507725M},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{miyato2017-virtual,
  author          = {{Miyato}, T. and {Maeda}, S.-i. and {Koyama}, M. and {Ishii}, S.},
  title           = {{Virtual Adversarial Training: a Regularization Method for Supervised and Semi-Supervised Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = apr,
  eprint          = {1704.03976},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv170403976M},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{mnih2007-three,
  author          = {Mnih, Andriy and Hinton, Geoffrey},
  title           = {Three new graphical models for statistical language modelling},
  year            = 2007,
  booktitle       = {Proceedings of the 24th international conference on Machine learning},
  organization    = {ACM},
  pages           = {641--648},
  timestamp       = {20190109T1305}
}

@InProceedings{mnih2009-scalable,
  author          = {Mnih, Andriy and Hinton, Geoffrey E},
  title           = {A Scalable Hierarchical Distributed Language Model},
  year            = 2009,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1081--1088},
  timestamp       = {20181201T1030}
}

@Article{mnih2013-playing,
  author          = {Volodymyr Mnih and Koray Kavukcuoglu and David Silver and Alex Graves and Ioannis Antonoglou and Daan Wierstra and
                  Martin A. Riedmiller},
  title           = {Playing Atari With Deep Reinforcement Learning},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1312.5602},
  url             = {http://arxiv.org/abs/1312.5602},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MnihKSGAWR13},
  keywords        = {rl, dqn},
  timestamp       = {20181201T1030}
}

@Article{mnih2014-recurrent,
  author          = {Volodymyr Mnih and Nicolas Heess and Alex Graves and Koray Kavukcuoglu},
  title           = {Recurrent Models of Visual Attention},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1406.6247},
  url             = {http://arxiv.org/abs/1406.6247},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MnihHGK14},
  timestamp       = {20181201T1030}
}

@Article{mnih2015-human,
  author          = {Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A.  and Veness, Joel and Bellemare, Marc G.
                  and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K.  and Ostrovski, Georg and Petersen, Stig and Beattie,
                  Charles and Sadik, Amir and Antonoglou, Ioannis and King, Helen and Kumaran, Dharshan and Wierstra, Daan and Legg, Shane
                  and Hassabis, Demis},
  title           = {Human-Level Control Through Deep Reinforcement Learning},
  journaltitle    = {Nature},
  year            = 2015,
  volume          = 518,
  number          = 7540,
  month           = {Feb},
  pages           = {529-533},
  note            = {Letter},
  issn            = {0028-0836},
  url             = {http://dx.doi.org/10.1038/nature14236},
  journal         = {Nature},
  day             = 26,
  keywords        = {rl, dqn},
  publisher       = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
  timestamp       = {20181201T1030}
}

@Article{mnih2016-asynchronous,
  author          = {Volodymyr Mnih and Adri{\`{a}} Puigdom{\`{e}}nech Badia and Mehdi Mirza and Alex Graves and Timothy P. Lillicrap and
                  Tim Harley and David Silver and Koray Kavukcuoglu},
  title           = {Asynchronous Methods for Deep Reinforcement Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.01783},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{mohamed2015-variational,
  author          = {{Mohamed}, S. and {Jimenez Rezende}, D.},
  title           = {{Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = sep,
  eprint          = {1509.08731},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{molavi2013-iolaus,
  author          = {Molavi Kakhki, Arash and Kliman-Silver, Chloe and Mislove, Alan},
  title           = {Iolaus: Securing online content rating systems},
  year            = 2013,
  booktitle       = {Proceedings of the 22nd international conference on World Wide Web},
  organization    = {ACM},
  pages           = {919--930},
  keywords        = {data, yelp, spam, bos, sf},
  timestamp       = {20181201T1030}
}

@Article{molchanov2016-pruning,
  author          = {Pavlo Molchanov and Stephen Tyree and Tero Karras and Timo Aila and Jan Kautz},
  title           = {Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.06440},
  journal         = {CoRR},
  keywords        = {pruning},
  timestamp       = {20181201T1030}
}

@Article{molchanov2017-variational,
  author          = {Molchanov, Dmitry and Ashukha, Arsenii and Vetrov, Dmitry},
  title           = {Variational Dropout Sparsifies Deep Neural Networks},
  journaltitle    = {arXiv preprint arXiv:1701.05369},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1701.05369},
  keywords        = {dropout, sparse, compress, mnist, cifar10, cnn},
  timestamp       = {20181201T1030}
}

@InProceedings{montana1989-training,
  author          = {Montana, David J. and Davis, Lawrence},
  title           = {Training Feedforward Neural Networks Using Genetic Algorithms},
  year            = 1989,
  booktitle       = {Proceedings of the 11th International Joint Conference on Artificial Intelligence - Volume 1},
  series          = {IJCAI'89},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  location        = {Detroit, Michigan},
  pages           = {762--767},
  url             = {http://dl.acm.org/citation.cfm?id=1623755.1623876},
  acmid           = 1623876,
  address         = {San Francisco, CA, USA},
  numpages        = 6,
  timestamp       = {20181201T1030}
}

@Article{montufar2014-number,
  author          = {{Mont{\'u}far}, G. and {Pascanu}, R. and {Cho}, K. and {Bengio}, Y.},
  title           = {{On the Number of Linear Regions of Deep Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = feb,
  eprint          = {1402.1869},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{moore1993-prioritized,
  author          = {Moore, Andrew W and Atkeson, Christopher G},
  title           = {Prioritized Sweeping: Reinforcement Learning With Less Data and Less Time},
  journaltitle    = {Machine Learning},
  year            = 1993,
  volume          = 13,
  number          = 1,
  pages           = {103--130},
  journal         = {Machine Learning},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{moosavi-dezfooli2015-deepfool,
  author          = {Seyed{-}Mohsen Moosavi{-}Dezfooli and Alhussein Fawzi and Pascal Frossard},
  title           = {Deepfool: a Simple and Accurate Method To Fool Deep Neural Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.04599},
  eprint          = {1511.04599},
  url             = {http://arxiv.org/abs/1511.04599},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/Moosavi-Dezfooli15},
  keywords        = {adversarial, attack, deepfool},
  timestamp       = {20181201T1030}
}

@Article{moosavi-dezfooli2016-universal,
  author          = {Moosavi-Dezfooli, Seyed-Mohsen and Fawzi, Alhussein and Fawzi, Omar and Frossard, Pascal},
  title           = {Universal Adversarial Perturbations},
  journaltitle    = {arXiv preprint arXiv:1610.08401},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1610.08401},
  keywords        = {adversarial},
  timestamp       = {20181201T1030}
}

@Article{moosavi-dezfooli2017-analysis,
  author          = {Seyed{-}Mohsen Moosavi{-}Dezfooli and Alhussein Fawzi and Omar Fawzi and Pascal Frossard and Stefano Soatto},
  title           = {Analysis of Universal Adversarial Perturbations},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1705.09554},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@Article{mopuri2017-fast,
  author          = {Mopuri, Konda Reddy and Garg, Utsav and Babu, R Venkatesh},
  title           = {Fast Feature Fool: a Data Independent Approach To Universal Adversarial Perturbations},
  journaltitle    = {arXiv preprint arXiv:1707.05572},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.05572},
  keywords        = {adversarial, attack, universal perturbation},
  timestamp       = {20181201T1030}
}

@InProceedings{morcos2018-insights,
  author          = {Morcos, Ari and Raghu, Maithra and Bengio, Samy},
  title           = {Insights on representational similarity in neural networks with canonical correlation},
  keywords        = {cca},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {5727--5736},
  timestamp       = {20190429T1337}
}

@InCollection{mordatch2015-interactive,
  author          = {Mordatch, Igor and Lowrey, Kendall and Andrew, Galen and Popovic, Zoran and Todorov, Emanuel V.},
  title           = {Interactive Control of Diverse Complex Characters with Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3132--3140},
  url             = {http://papers.nips.cc/paper/5764-interactive-control-of-diverse-complex-characters-with-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{mordatch2017-emergence,
  author          = {{Mordatch}, I. and {Abbeel}, P.},
  title           = {{Emergence of Grounded Compositional Language in Multi-Agent Populations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.04908},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@Article{morerio2017-curriculum,
  author          = {Pietro Morerio and Jacopo Cavazza and Riccardo Volpi and Ren{\'{e}} Vidal and Vittorio Murino},
  title           = {Curriculum Dropout},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.06229},
  url             = {http://arxiv.org/abs/1703.06229},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/MorerioCVVM17},
  timestamp       = {20181201T1030}
}

@Article{moriarty1997-forming,
  author          = {Moriarty, David E and Miikkulainen, Risto},
  title           = {Forming Neural Networks Through Efficient and Adaptive Coevolution},
  journaltitle    = {Evolutionary Computation},
  year            = 1997,
  volume          = 5,
  number          = 4,
  pages           = {373--399},
  journal         = {Evolutionary Computation},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@InProceedings{morin2005-hierarchical,
  author          = {Morin, Frederic and Bengio, Yoshua},
  title           = {Hierarchical Probabilistic Neural Network Language Model.},
  year            = 2005,
  booktitle       = {Aistats},
  volume          = 5,
  organization    = {Citeseer},
  pages           = {246--252},
  timestamp       = {20181201T1030}
}

@Article{morse2016-simple,
  author          = {Morse, Gregory and Stanley, Kenneth O},
  title           = {Simple Evolutionary Optimization Can Rival Stochastic Gradient Descent in Neural Networks},
  journaltitle    = {GECCO},
  year            = 2016,
  journal         = {GECCO},
  timestamp       = {20181201T1030}
}

@Article{movellan1998-learning,
  author          = {Movellan, Javier R.},
  title           = {A Learning Theorem for Networks At Detailed Stochastic Equilibrium},
  journaltitle    = {Neural Comput.},
  year            = 1998,
  volume          = 10,
  number          = 5,
  month           = jul,
  pages           = {1157--1178},
  issn            = {0899-7667},
  doi             = {10.1162/089976698300017395},
  url             = {https://doi.org/10.1162/089976698300017395},
  journal         = {Neural Comput.},
  acmid           = 295936,
  address         = {Cambridge, MA, USA},
  issue_date      = {July 1, 1998},
  numpages        = 22,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@InProceedings{mozer1989-skeletonization,
  author          = {Mozer, Michael C and Smolensky, Paul},
  title           = {Skeletonization: A technique for trimming the fat from a network via relevance assessment},
  year            = 1989,
  booktitle       = {Advances in neural information processing systems},
  pages           = {107--115},
  keywords        = {pruning, saliency},
  timestamp       = {20181201T1030}
}

@Article{mrazova2012-can,
  author          = "Iveta Mrazova and Marek Kukacka",
  title           = {Can Deep Neural Networks Discover Meaningful Pattern Features?},
  journaltitle    = "Procedia Computer Science",
  year            = 2012,
  volume          = 12,
  pages           = "194 - 199",
  issn            = "1877-0509",
  doi             = {10.1016/j.procs.2012.09.053},
  url             = {https://doi.org/10.1016/j.procs.2012.09.053},
  journal         = "Procedia Computer Science",
  keywords        = "convolutional neural networks",
  timestamp       = {20181201T1030}
}

@InProceedings{mrksic2016-counter,
  author          = {Nikola Mrk\v{s}i\'c and Diarmuid {\'O S\'eaghdha} and Blaise Thomson and Milica Ga\v{s}i\'c and Lina Rojas-Barahona and
                  Pei-Hao Su and David Vandyke and Tsung-Hsien Wen and Steve Young},
  title           = {Counter-fitting Word Vectors to Linguistic Constraints},
  year            = 2016,
  booktitle       = {Proceedings of HLT-NAACL},
  keywords        = {word2vec},
  timestamp       = {20181201T1030}
}

@InProceedings{mukherjee2013-what,
  author          = {Mukherjee, Arjun and Venkataraman, Vivek and Liu, Bing and Glance, Natalie S},
  title           = {What yelp fake review filter might be doing?},
  year            = 2013,
  booktitle       = {ICWSM},
  pages           = {409--418},
  keywords        = {data, yelp, spam, chi},
  timestamp       = {20181201T1030}
}

@Article{mumford2002-pattern,
  author          = {{Mumford}, David},
  title           = {{Pattern Theory: the Mathematics of perception}},
  journaltitle    = {arXiv Mathematics e-prints},
  year            = 2002,
  eid             = {math/0212400},
  month           = Nov,
  pages           = {math/0212400},
  eprint          = {math/0212400},
  journal         = {arXiv Mathematics e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/\#abs/2002math.....12400M},
  archiveprefix   = {arXiv},
  keywords        = {Mathematics - Numerical Analysis, Mathematics - Statistics, 60K35, 82B43},
  primaryclass    = {math.NA},
  timestamp       = {20190102T0950}
}

@Book{mumford2010-pattern,
  author          = {Mumford, David and Desolneux, Agn{\`e}s},
  title           = {Pattern theory: the stochastic analysis of real-world signals},
  year            = 2010,
  publisher       = {AK Peters/CRC Press},
  timestamp       = {20190102T0948}
}

@Article{mundt2017-building,
  author          = {{Mundt}, M. and {Weis}, T. and {Konda}, K. and {Ramesh}, V.},
  title           = {{Building Effective Deep Neural Network Architectures One Feature At a time}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.06778},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{murdoch2017-automatic,
  author          = {Murdoch, W James and Szlam, Arthur},
  title           = {Automatic Rule Extraction From Long Short Term Memory Networks},
  journaltitle    = {arXiv preprint arXiv:1702.02540},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.02540},
  keywords        = {interpret},
  timestamp       = {20181201T1030}
}

@InProceedings{murdoch2018-beyond,
  author          = {W. James Murdoch and Peter J. Liu and Bin Yu},
  title           = {Beyond Word Importance: Contextual Decomposition to Extract Interactions from {LSTM}s},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=rkRwGg-0Z},
  keywords        = {interpret, contextual decomposition, shapley},
  timestamp       = {20181201T1030}
}

@Book{murphy2012-machine,
  author          = {Murphy, Kevin P},
  title           = {Machine learning: a probabilistic perspective},
  year            = 2012,
  publisher       = {MIT press},
  timestamp       = {20181201T1030}
}

@Article{murray2015-auto,
  author          = {Kenton Murray and David Chiang},
  title           = {Auto-Sizing Neural Networks: With Applications To N-Gram Language Models},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1508.05051},
  journal         = {CoRR},
  keywords        = {pruning, dynamic},
  timestamp       = {20181201T1030}
}

@Article{mussmann2017-fast,
  author          = {{Mussmann}, S. and {Levy}, D. and {Ermon}, S.},
  title           = {{Fast Amortized Inference and Learning in Log-Linear Models With Randomly Perturbed Nearest Neighbor Search}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.03372},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{na2017-cascade,
  author          = {Na, Taesik and Ko, Jong Hwan and Mukhopadhyay, Saibal},
  title           = {Cascade Adversarial Machine Learning Regularized With a Unified Embedding},
  journaltitle    = {arXiv preprint arXiv:1708.02582},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1708.02582},
  timestamp       = {20181201T1030}
}

@InProceedings{nair2010-rectified,
  author          = {Vinod Nair and Geoffrey E. Hinton},
  title           = {Rectified Linear Units Improve Restricted Boltzmann Machines},
  year            = 2010,
  booktitle       = {Proceedings of the 27th International Conference on Machine Learning (ICML-10)},
  editor          = {Johannes F{\"u}rnkranz and Thorsten Joachims},
  publisher       = {Omnipress},
  pages           = {807-814},
  url             = {http://www.icml2010.org/papers/432.pdf},
  keywords        = {vgg16, vgg19},
  timestamp       = {20181201T1030}
}

@Article{nalisnick2015-scale,
  author          = {{Nalisnick}, E. and {Anandkumar}, A. and {Smyth}, P.},
  title           = {{A Scale Mixture Perspective of Multiplicative Noise in Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = jun,
  eprint          = {1506.03208},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2015arXiv150603208N},
  archiveprefix   = "arXiv",
  keywords        = {pruning, regularizer},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{nalisnick2018-do,
  author          = {{Nalisnick}, Eric and {Matsukawa}, Akihiro and {Teh}, Yee Whye and {Gorur}, Dilan and {Lakshminarayanan}, Balaji},
  title           = {{Do Deep Generative Models Know What They Don't Know?}},
  journaltitle    = {arXiv e-prints},
  year            = 2018,
  eid             = {arXiv:1810.09136},
  month           = Oct,
  pages           = {arXiv:1810.09136},
  eprint          = {1810.09136},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/#abs/2018arXiv181009136N},
  archiveprefix   = {arXiv},
  primaryclass    = {stat.ML},
  timestamp       = {20181207T1234}
}

@InCollection{nan2017-adaptive,
  author          = {Nan, Feng and Saligrama, Venkatesh},
  title           = {Adaptive Classification for Prediction Under a Budget},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4730--4740},
  url             = {http://papers.nips.cc/paper/7058-adaptive-classification-for-prediction-under-a-budget.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{narayanan2010-sample,
  author          = {Narayanan, Hariharan and Mitter, Sanjoy},
  title           = {Sample complexity of testing the manifold hypothesis},
  year            = 2010,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {1786--1794},
  timestamp       = {20181201T1030}
}

@InCollection{narayanaswamy2017-learning,
  author          = {Narayanaswamy, Siddharth and Paige, T. Brooks and van de Meent, Jan-Willem and Desmaison, Alban and Goodman, Noah and
                  Kohli, Pushmeet and Wood, Frank and Torr, Philip},
  title           = {Learning Disentangled Representations with Semi-Supervised Deep Generative Models},
  keywords        = {disentangle},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5927--5937},
  url             = {http://papers.nips.cc/paper/7174-learning-disentangled-representations-with-semi-supervised-deep-generative-models.pdf},
  timestamp       = {20181201T1030}
}

@Article{naud2017-burst,
  author          = {Naud, Richard and Sprekeler, Henning},
  title           = {Burst Ensemble Multiplexing: a Neural Code Connecting Dendritic Spikes With Microcircuits},
  journaltitle    = {bioRxiv},
  year            = 2017,
  doi             = {10.1101/143636},
  eprint          = {http://www.biorxiv.org/content/early/2017/06/30/143636.full.pdf},
  url             = {https://doi.org/10.1101/143636},
  journal         = {bioRxiv},
  publisher       = {Cold Spring Harbor Labs Journals},
  timestamp       = {20181201T1030}
}

@Book{neal2012-bayesian,
  author          = {Neal, Radford M},
  title           = {Bayesian learning for neural networks},
  year            = 2012,
  volume          = 118,
  publisher       = {Springer Science \& Business Media},
  keywords        = {pruning, bayesian},
  timestamp       = {20181201T1030}
}

@Book{nearing2010-mathematical,
  author          = {Nearing, James C and others},
  title           = {Mathematical tools for physics},
  year            = 2010,
  publisher       = {Dover Publications},
  timestamp       = {20181201T1030}
}

@Article{neelakantan2015-adding,
  author          = {Neelakantan, Arvind and Vilnis, Luke and Le, Quoc V and Sutskever, Ilya and Kaiser, Lukasz and Kurach, Karol and
                  Martens, James},
  title           = {Adding Gradient Noise Improves Learning for Very Deep Networks},
  journaltitle    = {arXiv preprint arXiv:1511.06807},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1511.06807},
  timestamp       = {20181201T1030}
}

@Article{neelakantan2015-efficient,
  author          = {Neelakantan, Arvind and Shankar, Jeevan and Passos, Alexandre and McCallum, Andrew},
  title           = {Efficient Non-Parametric Estimation of Multiple Embeddings Per Word in Vector Space},
  journaltitle    = {arXiv preprint arXiv:1504.06654},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1504.06654},
  timestamp       = {20181201T1030}
}

@Article{neelakantan2015-neural,
  author          = {Neelakantan, Arvind and Le, Quoc V and Sutskever, Ilya},
  title           = {Neural Programmer: Inducing Latent Programs With Gradient Descent},
  journaltitle    = {arXiv preprint arXiv:1511.04834},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1511.04834},
  timestamp       = {20181201T1030}
}

@Article{neelakantan2016-learning,
  author          = {Neelakantan, Arvind and Le, Quoc V and Abadi, Martin and McCallum, Andrew and Amodei, Dario},
  title           = {Learning a Natural Language Interface With Neural Programmer},
  journaltitle    = {arXiv preprint arXiv:1611.08945},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1611.08945},
  timestamp       = {20181201T1030}
}

@Article{neklyudov2018-variance,
  author          = {{Neklyudov}, K. and {Molchanov}, D. and {Ashukha}, A. and {Vetrov}, D.},
  title           = {{Variance Networks: When Expectation Does Not Meet Your Expectations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = mar,
  eprint          = {1803.03764},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180303764N},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Misc{neller2013-introduction,
  author          = {Neller, Todd W and Lanctot, Marc},
  title           = {An Introduction to Counterfactual Regret Minimization},
  year            = 2013,
  timestamp       = {20181201T1030}
}

@Article{nelson2008-exploiting,
  author          = {Nelson, Blaine and Barreno, Marco and Chi, Fuching Jack and Joseph, Anthony D and Rubinstein, Benjamin IP and Saini,
                  Udam and Sutton, Charles A and Tygar, J Doug and Xia, Kai},
  title           = {Exploiting Machine Learning To Subvert Your Spam Filter.},
  journaltitle    = {LEET},
  year            = 2008,
  volume          = 8,
  pages           = {1--9},
  journal         = {LEET},
  timestamp       = {20181201T1030}
}

@InCollection{nelson2009-misleading,
  author          = {Nelson, Blaine and Barreno, Marco and Chi, Fuching Jack and Joseph, Anthony D and Rubinstein, Benjamin IP and Saini,
                  Udam and Sutton, Charles and Tygar, JD and Xia, Kai},
  title           = {Misleading learners: Co-opting your spam filter},
  year            = 2009,
  booktitle       = {Machine learning in cyber trust},
  publisher       = {Springer},
  pages           = {17--51},
  timestamp       = {20181201T1030}
}

@Article{nesterov2008-confidence,
  author          = {Nesterov, Yu and Vial, J-Ph},
  title           = {Confidence Level Solutions for Stochastic Programming},
  journaltitle    = {Automatica},
  year            = 2008,
  volume          = 44,
  number          = 6,
  pages           = {1559--1568},
  journal         = {Automatica},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{nesterov2012-efficiency,
  author          = {Nesterov, Yu},
  title           = {Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems},
  journaltitle    = {SIAM Journal on Optimization},
  year            = 2012,
  volume          = 22,
  number          = 2,
  pages           = {341--362},
  journal         = {SIAM Journal on Optimization},
  publisher       = {SIAM},
  timestamp       = {20181201T1030}
}

@InProceedings{newell2016-stacked,
  author          = {Newell, Alejandro and Yang, Kaiyu and Deng, Jia},
  title           = {Stacked hourglass networks for human pose estimation},
  year            = 2016,
  booktitle       = {European Conference on Computer Vision},
  organization    = {Springer},
  pages           = {483--499},
  timestamp       = {20181201T1030}
}

@Article{neyshabur2016-path,
  author          = {Behnam Neyshabur and Yuhuai Wu and Ruslan Salakhutdinov and Nathan Srebro},
  title           = {Path-Normalized Optimization of Recurrent Neural Networks With Relu Activations},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1605.07154},
  url             = {http://arxiv.org/abs/1605.07154},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/NeyshaburWSS16},
  timestamp       = {20190113T0943}
}

@InCollection{neyshabur2017-exploring,
  author          = {Neyshabur, Behnam and Bhojanapalli, Srinadh and Mcallester, David and Srebro, Nati},
  title           = {Exploring Generalization in Deep Learning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5949--5958},
  url             = {http://papers.nips.cc/paper/7176-exploring-generalization-in-deep-learning.pdf},
  timestamp       = {20181201T1030}
}

@Article{neyshabur2018-towards,
  author          = {{Neyshabur}, B. and {Li}, Z. and {Bhojanapalli}, S. and {LeCun}, Y. and {Srebro}, N.},
  title           = {{Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = may,
  eprint          = {1805.12076},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180512076N},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InProceedings{ng1999-policy,
  author          = {Ng, Andrew Y and Harada, Daishi and Russell, Stuart},
  title           = {Policy invariance under reward transformations: Theory and application to reward shaping},
  year            = 1999,
  booktitle       = {ICML},
  volume          = 99,
  pages           = {278--287},
  timestamp       = {20181201T1030}
}

@InProceedings{ng2000-algorithms,
  author          = {Ng, Andrew Y. and Russell, Stuart J.},
  title           = {Algorithms for Inverse Reinforcement Learning},
  year            = 2000,
  booktitle       = {Proceedings of the Seventeenth International Conference on Machine Learning},
  series          = {ICML '00},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  isbn            = {1-55860-707-2},
  pages           = {663--670},
  url             = {http://dl.acm.org/citation.cfm?id=645529.657801},
  acmid           = 657801,
  address         = {San Francisco, CA, USA},
  numpages        = 8,
  timestamp       = {20181201T1030}
}

@InCollection{ng2002-discriminative,
  author          = {Andrew Y. Ng and Michael I. Jordan},
  title           = {On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes},
  year            = 2002,
  booktitle       = {Advances in Neural Information Processing Systems 14},
  editor          = {T.G. Dietterich and S. Becker and Z. Ghahramani},
  publisher       = {MIT Press},
  pages           = {841--848},
  url             = {http://papers.nips.cc/paper/2020-on-discriminative-vs-generative-classifiers-a-comparison-of-logistic-regression-and-naive-bayes.pdf},
  timestamp       = {20181201T1030}
}

@Misc{ng2011-cs294a,
  author          = {Andrew Ng},
  title           = {CS294A Lecture notes -- Sparse autoencoder},
  year            = 2011,
  url             = {https://web.stanford.edu/class/cs294a/sparseAutoencoder.pdf},
  urldate         = {2016-01-19},
  timestamp       = {20181201T1030}
}

@InProceedings{ngiam2010-tiled,
  author          = {Ngiam, Jiquan and Chen, Zhenghao and Chia, Daniel and Koh, Pang W and Le, Quoc V and Ng, Andrew Y},
  title           = {Tiled convolutional neural networks},
  year            = 2010,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1279--1287},
  timestamp       = {20181201T1030}
}

@InCollection{nguyen-phuoc2018-rendernet,
  author          = {Nguyen-Phuoc, Thu H and Li, Chuan and Balaban, Stephen and Yang, Yongliang},
  title           = {RenderNet: A deep convolutional network for differentiable rendering from 3D shapes},
  keywords        = {rendernet, differentiable renderer},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {7901--7911},
  url             = {http://papers.nips.cc/paper/8014-rendernet-a-deep-convolutional-network-for-differentiable-rendering-from-3d-shapes.pdf},
  timestamp       = {20181206T0906}
}

@Article{nguyen2014-deep,
  author          = {Anh Mai Nguyen and Jason Yosinski and Jeff Clune},
  title           = {Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.1897},
  url             = {http://arxiv.org/abs/1412.1897},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/NguyenYC14},
  timestamp       = {20181201T1030}
}

@InCollection{nguyen2015-inverse,
  author          = {Nguyen, Quoc Phong and Low, Bryan Kian Hsiang and Jaillet, Patrick},
  title           = {Inverse Reinforcement Learning with Locally Consistent Reward Functions},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1747--1755},
  url             = {http://papers.nips.cc/paper/5882-inverse-reinforcement-learning-with-locally-consistent-reward-functions.pdf},
  timestamp       = {20181201T1030}
}

@Article{nguyen2016-multifaceted,
  author          = {Nguyen, Anh and Yosinski, Jason and Clune, Jeff},
  title           = {Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural
                  Networks},
  journaltitle    = {arXiv preprint arXiv:1602.03616},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1602.03616},
  timestamp       = {20181201T1030}
}

@InProceedings{nguyen2017-plug,
  author          = {Nguyen, Anh and Clune, Jeff and Bengio, Yoshua and Dosovitskiy, Alexey and Yosinski, Jason},
  title           = {Plug \& Play Generative Networks: Conditional Iterative Generation of Images in Latent Space},
  year            = 2017,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  organization    = {IEEE},
  keywords        = {ppgn},
  timestamp       = {20181201T1030}
}

@Book{nilsson1996-introduction,
  author          = {Nilsson, Nils J},
  title           = {Introduction to machine learning. An early draft of a proposed textbook},
  year            = 1996,
  publisher       = {Citeseer},
  timestamp       = {20181201T1030}
}

@InProceedings{nitzberg1990-sketch,
  author          = {Nitzberg, Mark and Mumford, David},
  title           = {The 2.1-D Sketch},
  year            = 1990,
  booktitle       = {Computer Vision, 1990. Proceedings, Third International Conference on},
  organization    = {IEEE},
  pages           = {138--144},
  timestamp       = {20190102T1105}
}

@Article{niu2011-hogwild,
  author          = {{Niu}, F. and {Recht}, B. and {Re}, C. and {Wright}, S.~J.},
  title           = {{HOGWILD!: a Lock-Free Approach To Parallelizing Stochastic Gradient Descent}},
  journaltitle    = {ArXiv e-prints},
  year            = 2011,
  month           = jun,
  eprint          = {1106.5730},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Mathematics - Optimization and Control, Computer Science - Learning},
  primaryclass    = "math.OC",
  timestamp       = {20181201T1030}
}

@Book{nivre2006-inductive,
  author          = {Nivre, Joakim},
  title           = {Inductive dependency parsing},
  year            = 2006,
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{noekland2015-improving,
  author          = {N{\o}kland, Arild},
  title           = {Improving Back-Propagation By Adding an Adversarial Gradient},
  journaltitle    = {arXiv preprint arXiv:1510.04189},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1510.04189},
  timestamp       = {20181201T1030}
}

@Article{nogueira2016-webnav,
  author          = {Rodrigo Nogueira and Kyunghyun Cho},
  title           = {Webnav: {A} New Large-Scale Task for Natural Language Based Sequential Decision Making},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.02261},
  url             = {http://arxiv.org/abs/1602.02261},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/NogueiraC16},
  timestamp       = {20181201T1030}
}

@InCollection{noh2017-regularizing,
  author          = {Noh, Hyeonwoo and You, Tackgeun and Mun, Jonghwan and Han, Bohyung},
  title           = {Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5115--5124},
  url             = {http://papers.nips.cc/paper/7096-regularizing-deep-neural-networks-by-noise-its-interpretation-and-optimization.pdf},
  timestamp       = {20181201T1030}
}

@Article{norouzi2016-reward,
  author          = {Mohammad Norouzi and Samy Bengio and Zhifeng Chen and Navdeep Jaitly and Mike Schuster and Yonghui Wu and Dale
                  Schuurmans},
  title           = {Reward Augmented Maximum Likelihood for Neural Structured Prediction},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.00150},
  url             = {http://arxiv.org/abs/1609.00150},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/NorouziBCJSWS16},
  timestamp       = {20181201T1030}
}

@Article{norton2017-adversarial,
  author          = {Norton, Andrew P and Qi, Yanjun},
  title           = {Adversarial-Playground: a Visualization Suite Showing How Adversarial Examples Fool Deep Learning},
  journaltitle    = {arXiv preprint arXiv:1708.00807},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1708.00807},
  timestamp       = {20181201T1030}
}

@InProceedings{novak2018-sensitivity,
  author          = {Roman Novak and Yasaman Bahri and Daniel A. Abolafia and Jeffrey Pennington and Jascha Sohl-Dickstein},
  title           = {Sensitivity and Generalization in Neural Networks: an Empirical Study},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HJC2SzZCW},
  timestamp       = {20181201T1030}
}

@InCollection{novikov2015-tensorizing,
  author          = {Novikov, Alexander and Podoprikhin, Dmitrii and Osokin, Anton and Vetrov, Dmitry P},
  title           = {Tensorizing Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {442--450},
  url             = {http://papers.nips.cc/paper/5787-tensorizing-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{nowak2000-evolution,
  author          = {Nowak, Martin A.  and Plotkin, Joshua B.  and Jansen, Vincent A. A.},
  title           = {The Evolution of Syntactic Communication},
  journaltitle    = {Nature},
  year            = 2000,
  volume          = 404,
  number          = 6777,
  month           = {Mar},
  pages           = {495-498},
  issn            = {0028-0836},
  doi             = {10.1038/35006635},
  url             = {https://doi.org/10.1038/35006635},
  journal         = {Nature},
  day             = 30,
  publisher       = {Macmillian Magazines Ltd.},
  timestamp       = {20181201T1030}
}

@InProceedings{nowak2018-divide,
  author          = {Alex Nowak and David Folqu{\'e} and Joan Bruna},
  title           = {Divide and Conquer Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=B1jscMbAW},
  timestamp       = {20181201T1030}
}

@Article{nowlan1992-simplifying,
  author          = {Nowlan, Steven J and Hinton, Geoffrey E},
  title           = {Simplifying Neural Networks By Soft Weight-Sharing},
  journaltitle    = {Neural computation},
  year            = 1992,
  volume          = 4,
  number          = 4,
  pages           = {473--493},
  journal         = {Neural computation},
  keywords        = {quantization, regularizer, soft weight sharing},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{o2010-play,
  author          = {O' Neill, Joseph and Pleydell-Bouverie, Barty and Dupret, David and Csicsvari, Jozsef},
  title           = {Play It Again: Reactivation of Waking Experience and Memory},
  journaltitle    = {Trends in neurosciences},
  year            = 2010,
  volume          = 33,
  number          = 5,
  pages           = {220--229},
  journal         = {Trends in neurosciences},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{obuchi2009-weight,
  author          = {Obuchi, Tomoyuki and Kabashima, Yoshiyuki},
  title           = {Weight Space Structure and Analysis Using a Finite Replica Number in the Ising Perceptron},
  journaltitle    = {Journal of Statistical Mechanics: Theory and Experiment},
  year            = 2009,
  volume          = 2009,
  number          = 12,
  pages           = {P12014},
  journal         = {Journal of Statistical Mechanics: Theory and Experiment},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1030}
}

@Article{oconnor2005-graded,
  author          = {O'Connor, Daniel H and Wittenberg, Gayle M and Wang, Samuel S-H},
  title           = {Graded Bidirectional Synaptic Plasticity Is Composed of Switch-Like Unitary Events},
  journaltitle    = {Proceedings of the National Academy of Sciences of the United States of America},
  year            = 2005,
  volume          = 102,
  number          = 27,
  pages           = {9679--9684},
  journal         = {Proceedings of the National Academy of Sciences of the United States of America},
  keywords        = {biology, quantization},
  publisher       = {National Acad Sciences},
  timestamp       = {20181201T1030}
}

@InProceedings{oconnor2018-temporally,
  author          = {Peter O'Connor and Efstratios Gavves and Matthias Reisser and Max Welling},
  title           = {Temporally Efficient Deep Learning with Spikes},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HkZy-bW0-},
  timestamp       = {20181201T1030}
}

@InCollection{oh2015-action,
  author          = {Oh, Junhyuk and Guo, Xiaoxiao and Lee, Honglak and Lewis, Richard L and Singh, Satinder},
  title           = {Action-Conditional Video Prediction using Deep Networks in Atari Games},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2863--2871},
  url             = {http://papers.nips.cc/paper/5859-action-conditional-video-prediction-using-deep-networks-in-atari-games.pdf},
  timestamp       = {20181201T1030}
}

@Article{oh2016-faceless,
  author          = {Oh, Seong Joon and Benenson, Rodrigo and Fritz, Mario and Schiele, Bernt},
  title           = {Faceless Person Recognition; Privacy Implications in Social Media},
  journaltitle    = {arXiv preprint arXiv:1607.08438},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1607.08438},
  timestamp       = {20181201T1030}
}

@InProceedings{oh2018-towards,
  author          = {Seong Joon Oh and Max Augustin and Mario Fritz and Bernt Schiele},
  title           = {Towards Reverse-Engineering Black-Box Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BydjJte0-},
  timestamp       = {20181201T1030}
}

@Article{oland2017-be,
  author          = {Oland, Anders and Bansal, Aayush and Dannenberg, Roger B and Raj, Bhiksha},
  title           = {Be Careful What You Backpropagate: a Case for Linear Output Activations \& Gradient Boosting},
  journaltitle    = {arXiv preprint arXiv:1707.04199},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.04199},
  timestamp       = {20181201T1030}
}

@Article{olshausen1997-sparse,
  author          = "Bruno A. Olshausen and David J. Field",
  title           = {Sparse Coding With an Overcomplete Basis Set: a Strategy Employed By V1?},
  journaltitle    = "Vision Research",
  year            = 1997,
  volume          = 37,
  number          = 23,
  pages           = "3311 - 3325",
  issn            = "0042-6989",
  doi             = {10.1016/S0042-6989(97)00169-7},
  url             = {https://doi.org/10.1016/S0042-6989(97)00169-7},
  journal         = "Vision Research",
  keywords        = "Coding",
  keywords        = "Coding",
  keywords        = "Coding",
  keywords        = "Coding",
  timestamp       = {20181201T1030}
}

@Article{oord2016-pixel,
  author          = {A{\"{a}}ron van den Oord and Nal Kalchbrenner and Koray Kavukcuoglu},
  title           = {Pixel Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1601.06759},
  eprint          = {1601.06759},
  url             = {http://arxiv.org/abs/1601.06759},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/OordKK16},
  keywords        = {pixelcnn},
  timestamp       = {20181201T1030}
}

@Article{oord2016-wavenet,
  author          = {A{\"{a}}ron van den Oord and Sander Dieleman and Heiga Zen and Karen Simonyan and Oriol Vinyals and Alex Graves and Nal
                  Kalchbrenner and Andrew W. Senior and Koray Kavukcuoglu},
  title           = {Wavenet: {A} Generative Model for Raw Audio},
  keywords        = {wavenet},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.03499},
  eprint          = {1609.03499},
  url             = {http://arxiv.org/abs/1609.03499},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/OordDZSVGKSK16},
  timestamp       = {20190109T1404}
}

@Article{orabona2017-backprop,
  author          = {Francesco Orabona and Tatiana Tommasi},
  title           = {Backprop Without Learning Rates Through Coin Betting},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1705.07795},
  url             = {http://arxiv.org/abs/1705.07795},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/OrabonaT17},
  timestamp       = {20181201T1030}
}

@InCollection{orabona2017-training,
  author          = {Orabona, Francesco and Tommasi, Tatiana},
  title           = {Training Deep Networks without Learning Rates Through Coin Betting},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2157--2167},
  url             = {http://papers.nips.cc/paper/6811-training-deep-networks-without-learning-rates-through-coin-betting.pdf},
  timestamp       = {20181201T1030}
}

@Book{orr2003-neural,
  author          = {Orr, Genevieve B and M{\"u}ller, Klaus-Robert},
  title           = {Neural networks: tricks of the trade},
  year            = 2003,
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@InProceedings{palatucci2009-zero,
  author          = {Palatucci, Mark and Pomerleau, Dean and Hinton, Geoffrey E and Mitchell, Tom M},
  title           = {Zero-shot learning with semantic output codes},
  year            = 2009,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1410--1418},
  timestamp       = {20181201T1030}
}

@Article{pan2015-expressiveness,
  author          = {Xingyuan Pan and Vivek Srikumar},
  title           = {Expressiveness of Rectifier Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.05678},
  url             = {http://arxiv.org/abs/1511.05678},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/PanS15},
  timestamp       = {20181201T1030}
}

@Article{pang2017-towards,
  author          = {Tianyu Pang and Chao Du and Jun Zhu},
  title           = {Towards Robust Detection of Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.00633},
  journal         = {CoRR},
  keywords        = {adversarial, defense},
  timestamp       = {20181201T1030}
}

@Article{papernot2015-distillation,
  author          = {Nicolas Papernot and Patrick Drew McDaniel and Xi Wu and Somesh Jha and Ananthram Swami},
  title           = {Distillation As a Defense To Adversarial Perturbations Against Deep Neural Networks},
  keywords        = {adversarial, distill},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.04508},
  url             = {http://arxiv.org/abs/1511.04508},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/PapernotMWJS15},
  timestamp       = {20181201T1030}
}

@Article{papernot2015-limitations,
  author          = {Nicolas Papernot and Patrick McDaniel and Somesh Jha and Matt Fredrikson and Z. Berkay Celik and Ananthram Swami},
  title           = {The Limitations of Deep Learning in Adversarial Settings},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.07528},
  url             = {http://arxiv.org/abs/1511.07528},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/PapernotMJFCS15},
  keywords        = {adversarial, jsma},
  timestamp       = {20181201T1030}
}

@Article{papernot2016-crafting,
  author          = {Nicolas Papernot and Patrick McDaniel and Ananthram Swami and Richard E. Harang},
  title           = {Crafting Adversarial Input Sequences for Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.08275},
  url             = {http://arxiv.org/abs/1604.08275},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/PapernotMSH16},
  timestamp       = {20181201T1030}
}

@Article{papernot2016-practical,
  author          = {Nicolas Papernot and Patrick Drew McDaniel and Ian J. Goodfellow and Somesh Jha and Z. Berkay Celik and Ananthram
                  Swami},
  title           = {Practical Black-Box Attacks Against Deep Learning Systems Using Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.02697},
  url             = {http://arxiv.org/abs/1602.02697},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/PapernotMGJCS16},
  keywords        = {adversarial, attack},
  timestamp       = {20181201T1030}
}

@Article{papernot2016-semi,
  author          = {Papernot, Nicolas and Abadi, Mart{\'\i}n and Erlingsson, {\'U}lfar and Goodfellow, Ian and Talwar, Kunal},
  title           = {Semi-Supervised Knowledge Transfer for Deep Learning From Private Training Data},
  journaltitle    = {arXiv preprint arXiv:1610.05755},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1610.05755},
  timestamp       = {20181201T1030}
}

@Article{papernot2016-transferability,
  author          = {{Papernot}, N. and {McDaniel}, P. and {Goodfellow}, I.},
  title           = {{Transferability in Machine Learning: From Phenomena To Black-Box Attacks Using Adversarial Samples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = may,
  eprint          = {1605.07277},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, transferability},
  primaryclass    = "cs.CR",
  timestamp       = {20181201T1030}
}

@InProceedings{papineni2002-bleu,
  author          = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing},
  title           = {BLEU: a method for automatic evaluation of machine translation},
  year            = 2002,
  booktitle       = {Proceedings of the 40th annual meeting on association for computational linguistics},
  organization    = {Association for Computational Linguistics},
  pages           = {311--318},
  keywords        = {bleu},
  timestamp       = {20181201T1030}
}

@Article{parikh2016-decomposable,
  author          = {Parikh, Ankur P and T{\"a}ckstr{\"o}m, Oscar and Das, Dipanjan and Uszkoreit, Jakob},
  title           = {A Decomposable Attention Model for Natural Language Inference},
  journaltitle    = {arXiv preprint arXiv:1606.01933},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1606.01933},
  keywords        = {attention, self attention},
  timestamp       = {20181201T1030}
}

@Article{parisi1994-gauge,
  author          = {{Parisi}, G.},
  title           = {{Gauge Theories, Spin Glasses and Real Glasses}},
  journaltitle    = {eprint arXiv:cond-mat/9411115},
  year            = 1994,
  month           = nov,
  eprint          = {cond-mat/9411115},
  journal         = {eprint arXiv:cond-mat/9411115},
  keywords        = {Condensed Matter, High Energy Physics - Theory},
  timestamp       = {20181201T1030}
}

@Article{parisi1994-replica,
  author          = {Giorgio Parisi},
  title           = {{On the Replica Approach To Spin Glass}},
  journaltitle    = {eprint arXiv:cond-mat/9412004},
  year            = 1994,
  month           = dec,
  eprint          = {cond-mat/9412004},
  journal         = {eprint arXiv:cond-mat/9412004},
  keywords        = {Condensed Matter},
  timestamp       = {20181201T1030}
}

@Article{parisi2002-physical,
  author          = {{Parisi}, G.},
  title           = {{The Physical Meaning of Replica Symmetry Breaking}},
  journaltitle    = {eprint arXiv:cond-mat/0205387},
  year            = 2002,
  month           = may,
  eprint          = {cond-mat/0205387},
  journal         = {eprint arXiv:cond-mat/0205387},
  keywords        = {Statistical Mechanics, Disordered Systems and Neural Networks},
  timestamp       = {20181201T1030}
}

@Article{park2017-adversarial,
  author          = {Park, Sungrae and Park, Jun-Keon and Shin, Su-Jin and Moon, Il-Chul},
  title           = {Adversarial Dropout for Supervised and Semi-Supervised Learning},
  journaltitle    = {arXiv preprint arXiv:1707.03631},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.03631},
  timestamp       = {20181201T1030}
}

@InProceedings{park2017-faster,
  author          = {Park, J and Li, S and Wen, W and Tang, PTP and Li, H and Chen, Y and Dubey, P},
  title           = {Faster cnns with direct sparse convolutions and guided pruning},
  year            = 2017,
  booktitle       = {International Conference on Learning Representations (ICLR)},
  volume          = 1,
  number          = 2,
  pages           = 8,
  keywords        = {cnn, pruning, sparse, compress, imagenet},
  timestamp       = {20181201T1030}
}

@Article{pascanu2012-understanding,
  author          = {Razvan Pascanu and Tomas Mikolov and Yoshua Bengio},
  title           = {Understanding the Exploding Gradient Problem},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1211.5063},
  url             = {http://arxiv.org/abs/1211.5063},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1211-5063},
  timestamp       = {20181201T1030}
}

@InProceedings{pascanu2013-difficulty,
  author          = {Pascanu, Razvan and Mikolov, Tomas and Bengio, Yoshua},
  title           = {On the Difficulty of Training Recurrent Neural Networks},
  year            = 2013,
  booktitle       = {International Conference on Machine Learning},
  pages           = {1310--1318},
  keywords        = {gradient clipping, rnn},
  timestamp       = {20181201T1030}
}

@Article{pascanu2013-number,
  author          = {Pascanu, Razvan and Montufar, Guido and Bengio, Yoshua},
  title           = {On the Number of Response Regions of Deep Feed Forward Networks With Piece-Wise Linear Activations},
  journaltitle    = {arXiv preprint arXiv:1312.6098},
  year            = 2013,
  journal         = {arXiv preprint arXiv:1312.6098},
  timestamp       = {20181201T1030}
}

@Article{pascanu2014-saddle,
  author          = {Razvan Pascanu and Yann N. Dauphin and Surya Ganguli and Yoshua Bengio},
  title           = {On the Saddle Point Problem for Non-Convex Optimization},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1405.4604},
  url             = {http://arxiv.org/abs/1405.4604},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/PascanuDGB14},
  timestamp       = {20181201T1030}
}

@InProceedings{pascanu2015-malware,
  author          = {Pascanu, Razvan and Stokes, Jack W and Sanossian, Hermineh and Marinescu, Mady and Thomas, Anil},
  title           = {Malware classification with recurrent networks},
  year            = 2015,
  booktitle       = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  organization    = {IEEE},
  pages           = {1916--1920},
  timestamp       = {20181201T1030}
}

@Article{pathak2017-using,
  author          = {{Pathak}, J. and {Lu}, Z. and {Hunt}, B.~R. and {Girvan}, M. and {Ott}, E.},
  title           = {{Using Machine Learning To Replicate Chaotic Attractors and Calculate Lyapunov Exponents From data}},
  journaltitle    = {Chaos},
  year            = 2017,
  volume          = 27,
  number          = 12,
  eid             = 121102,
  month           = dec,
  pages           = 121102,
  doi             = {10.1063/1.5010300},
  eprint          = {1710.07313},
  url             = {https://doi.org/10.1063/1.5010300},
  journal         = {Chaos},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017Chaos..27l1102P},
  archiveprefix   = "arXiv",
  keywords        = {chaos},
  primaryclass    = "nlin.CD",
  timestamp       = {20181201T1030}
}

@Article{pathak2018-model,
  author          = {Pathak, Jaideep and Hunt, Brian and Girvan, Michelle and Lu, Zhixin and Ott, Edward},
  title           = {Model-Free Prediction of Large Spatiotemporally Chaotic Systems From Data: a Reservoir Computing Approach},
  journaltitle    = {Phys. Rev. Lett.},
  year            = 2018,
  volume          = 120,
  issue           = 2,
  month           = {Jan},
  pages           = 024102,
  doi             = {10.1103/PhysRevLett.120.024102},
  url             = {https://doi.org/10.1103/PhysRevLett.120.024102},
  journal         = {Phys. Rev. Lett.},
  keywords        = {chaos},
  numpages        = 5,
  publisher       = {American Physical Society},
  timestamp       = {20181201T1030}
}

@Book{pathria2011-statistical,
  author          = {Pathria, R. K. and Beale, Paul D.},
  title           = {Statistical Mechanics},
  year            = 2011,
  edition         = 3,
  publisher       = {Elsevier Ltd},
  timestamp       = {20181201T1030}
}

@Article{paulus2017-deep,
  author          = {Paulus, Romain and Xiong, Caiming and Socher, Richard},
  title           = {A Deep Reinforced Model for Abstractive Summarization},
  journaltitle    = {arXiv preprint arXiv:1705.04304},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.04304},
  keywords        = {attention, self attention},
  timestamp       = {20181201T1030}
}

@Article{pearl2018-theoretical,
  author          = {Judea Pearl},
  title           = {Theoretical Impediments To Machine Learning With Seven Sparks From the Causal Revolution},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1801.04016},
  eprint          = {1801.04016},
  url             = {http://arxiv.org/abs/1801.04016},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1801-04016},
  keywords        = {causal, structural causal model, scm},
  timestamp       = {20181201T1030}
}

@InCollection{peck2017-lower,
  author          = {Peck, Jonathan and Roels, Joris and Goossens, Bart and Saeys, Yvan},
  title           = {Lower bounds on the robustness to adversarial perturbations},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {804--813},
  url             = {http://papers.nips.cc/paper/6682-lower-bounds-on-the-robustness-to-adversarial-perturbations.pdf},
  keywords        = {adversarial, theory},
  timestamp       = {20181201T1030}
}

@InProceedings{pedersen2004-wordnet,
  author          = {Pedersen, Ted and Patwardhan, Siddharth and Michelizzi, Jason},
  title           = {WordNet::Similarity: measuring the relatedness of concepts},
  year            = 2004,
  booktitle       = {Demonstration papers at HLT-NAACL 2004},
  organization    = {Association for Computational Linguistics},
  pages           = {38--41},
  timestamp       = {20181201T1030}
}

@InProceedings{pedersoli2018-espresso,
  author          = {Fabrizio Pedersoli and George Tzanetakis and Andrea Tagliasacchi},
  title           = {Espresso: Efficient Forward Propagation for Binary Deep Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=Sk6fD5yCb},
  timestamp       = {20181201T1030}
}

@Article{pehlevan2015-hebbian,
  author          = {{Pehlevan}, C. and {Hu}, T. and {Chklovskii}, D.~B.},
  title           = {{A Hebbian/anti-Hebbian Neural Network for Linear Subspace Learning: a Derivation From Multidimensional Scaling of
                  Streaming Data}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = mar,
  eprint          = {1503.00669},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Quantitative Biology - Neurons and Cognition, Computer Science - Neural and Evolutionary Computing, Statistics -
                  Machine Learning},
  primaryclass    = "q-bio.NC",
  timestamp       = {20181201T1030}
}

@InCollection{pehlevan2015-normative,
  author          = {Pehlevan, Cengiz and Chklovskii, Dmitri},
  title           = {A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2269--2277},
  url             = {http://papers.nips.cc/paper/5885-a-normative-theory-of-adaptive-dimensionality-reduction-in-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{pei2017-deepxplore,
  author          = {Pei, Kexin and Cao, Yinzhi and Yang, Junfeng and Jana, Suman},
  title           = {Deepxplore: Automated whitebox testing of deep learning systems},
  year            = 2017,
  booktitle       = {Proceedings of the 26th Symposium on Operating Systems Principles},
  organization    = {ACM},
  pages           = {1--18},
  keywords        = {adversarial, attack, deepxplore},
  timestamp       = {20181201T1030}
}

@Article{peng2016-terrain,
  author          = {Xue Bin Peng and Glen Berseth and Michiel van de Panne},
  title           = {Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning},
  journaltitle    = {ACM Transactions on Graphics (Proc. SIGGRAPH 2016)},
  year            = 2016,
  volume          = 35,
  number          = 5,
  note            = {to appear},
  journal         = {ACM Transactions on Graphics (Proc. SIGGRAPH 2016)},
  timestamp       = {20181201T1030}
}

@InProceedings{pennington2014-glove,
  author          = {Pennington, Jeffrey and Socher, Richard and Manning, Christopher},
  title           = {Glove: Global vectors for word representation},
  year            = 2014,
  booktitle       = {Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
  pages           = {1532--1543},
  keywords        = {embedding, glove},
  timestamp       = {20181201T1030}
}

@Article{perozzi2014-deepwalk,
  author          = {Bryan Perozzi and Rami Al{-}Rfou and Steven Skiena},
  title           = {Deepwalk: Online Learning of Social Representations},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1403.6652},
  eprint          = {1403.6652},
  url             = {http://arxiv.org/abs/1403.6652},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/PerozziAS14},
  keywords        = {embedding, network, deepwalk},
  timestamp       = {20181201T1030}
}

@Article{peters2017-semi,
  author          = {Peters, Matthew E and Ammar, Waleed and Bhagavatula, Chandra and Power, Russell},
  title           = {Semi-Supervised Sequence Tagging With Bidirectional Language Models},
  keywords        = {data, ner},
  journaltitle    = {arXiv preprint arXiv:1705.00108},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.00108},
  timestamp       = {20190107T0953}
}

@InProceedings{peters2018-deep,
  author          = {Peters, Matthew E. and Neumann, Mark and Iyyer, Mohit and Gardner, Matt and Clark, Christopher and Lee, Kenton and
                  Zettlemoyer, Luke},
  title           = {Deep contextualized word representations},
  keywords        = {embedding, word, elmo, polysemy},
  year            = 2018,
  booktitle       = {Proc. of NAACL},
  timestamp       = {20190103T1619}
}

@Book{petersen2012-matrix,
  author          = {Kaare Brandt Petersen and Michael Syskind Pedersen},
  title           = {The Matrix Cookbook},
  year            = 2012,
  pagetotal       = 72,
  key             = {matrix algebra, matrix relations, matrix identities, derivative of determinant, derivative of inverse matrix,
                  differentiate a matrix},
  timestamp       = {20181201T1030}
}

@Article{petroski2017-deep,
  author          = {{Petroski Such}, F. and {Madhavan}, V. and {Conti}, E. and {Lehman}, J. and {Stanley}, K.~O. and {Clune}, J.},
  title           = {{Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for
                  Reinforcement Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.06567},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171206567P},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Neural and Evolutionary Computing, Computer Science - Learning},
  timestamp       = {20181201T1030}
}

@InProceedings{pham2018-efficient,
  author          = {Pham, Hieu and Guan, Melody and Zoph, Barret and Le, Quoc and Dean, Jeff},
  title           = {Efficient Neural Architecture Search via Parameters Sharing},
  year            = 2018,
  booktitle       = {Proceedings of the 35th International Conference on Machine Learning},
  editor          = {Dy, Jennifer and Krause, Andreas},
  volume          = 80,
  series          = {Proceedings of Machine Learning Research},
  publisher       = {PMLR},
  month           = {10--15 Jul},
  pages           = {4095--4104},
  url             = {http://proceedings.mlr.press/v80/pham18a.html},
  address         = {Stockholmsm{\"a}ssan, Stockholm Sweden},
  keywords        = {nas},
  pdf             = {http://proceedings.mlr.press/v80/pham18a/pham18a.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{piech2015-deep,
  author          = {Piech, Chris and Bassen, Jonathan and Huang, Jonathan and Ganguli, Surya and Sahami, Mehran and Guibas, Leonidas J and
                  Sohl-Dickstein, Jascha},
  title           = {Deep Knowledge Tracing},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {505--513},
  url             = {http://papers.nips.cc/paper/5654-deep-knowledge-tracing.pdf},
  timestamp       = {20181201T1030}
}

@Article{pinto2009-high,
  author          = {Pinto, Nicolas and Doukhan, David and DiCarlo, James J and Cox, David D},
  title           = {A High-Throughput Screening Approach To Discovering Good Forms of Biologically Inspired Visual Representation},
  journaltitle    = {PLoS computational biology},
  year            = 2009,
  volume          = 5,
  number          = 11,
  pages           = {e1000579},
  journal         = {PLoS computational biology},
  keywords        = {random},
  publisher       = {Public Library of Science},
  timestamp       = {20181201T1030}
}

@InProceedings{pinto2011-comparing,
  author          = {Pinto, Nicolas and Barhomi, Youssef and Cox, David D and DiCarlo, James J},
  title           = {Comparing state-of-the-art visual features on invariant object recognition tasks},
  year            = 2011,
  booktitle       = {Applications of computer vision (WACV), 2011 IEEE workshop on},
  organization    = {IEEE},
  pages           = {463--470},
  timestamp       = {20181201T1030}
}

@Article{pinto2017-robust,
  author          = {{Pinto}, L. and {Davidson}, J. and {Sukthankar}, R. and {Gupta}, A.},
  title           = {{Robust Adversarial Reinforcement Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.02702},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Multiagent Systems,
                  Computer Science - Robotics},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{pkalska2006-prototype,
  author          = {Pkalska, Elbieta and Duin, Robert P. W. and Pacl\'{\i}k, Pavel},
  title           = {Prototype Selection for Dissimilarity-Based Classifiers},
  journaltitle    = {Pattern Recogn.},
  year            = 2006,
  volume          = 39,
  number          = 2,
  month           = feb,
  pages           = {189--208},
  issn            = {0031-3203},
  doi             = {10.1016/j.patcog.2005.06.012},
  url             = {https://doi.org/10.1016/j.patcog.2005.06.012},
  journal         = {Pattern Recogn.},
  acmid           = 1221359,
  address         = {New York, NY, USA},
  issue_date      = {February, 2006},
  keywords        = {Dissimilarity, Nearest neighbor rule, Normal density based classifiers, Prototype selection, Representation},
  numpages        = 20,
  publisher       = {Elsevier Science Inc.},
  timestamp       = {20181201T1030}
}

@InCollection{platanios2017-estimating,
  author          = {Platanios, Emmanouil and Poon, Hoifung and Mitchell, Tom M and Horvitz, Eric J},
  title           = {Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4364--4373},
  url             = {http://papers.nips.cc/paper/7023-estimating-accuracy-from-unlabeled-data-a-probabilistic-logic-approach.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{platt2012-computational,
  author          = {Platt, John and Zweig, Geoffrey and Meek, Chris and Burges, Chris J.C. and and Liu, Qiang},
  title           = {Computational Approaches to Sentence Completion},
  year            = 2012,
  booktitle       = {ACL 2012},
  publisher       = {ACL/SIGPARSE},
  month           = {July},
  url             = {https://www.microsoft.com/en-us/research/publication/computational-approaches-to-sentence-completion/},
  timestamp       = {20181201T1030}
}

@InCollection{pleiss2017-fairness,
  author          = {Pleiss, Geoff and Raghavan, Manish and Wu, Felix and Kleinberg, Jon and Weinberger, Kilian Q},
  title           = {On Fairness and Calibration},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5684--5693},
  url             = {http://papers.nips.cc/paper/7151-on-fairness-and-calibration.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{polino2018-model,
  author          = {Antonio Polino and Razvan Pascanu and Dan Alistarh},
  title           = {Model Compression via Distillation and Quantization},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=S1XolQbRW},
  timestamp       = {20181201T1030}
}

@Article{poole2016-exponential,
  author          = {{Poole}, B. and {Lahiri}, S. and {Raghu}, M. and {Sohl-Dickstein}, J. and {Ganguli}, S.},
  title           = {{Exponential Expressivity in Deep Neural Networks Through Transient chaos}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.05340},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{prados1993-fast,
  author          = {D. L. Prados},
  title           = {A Fast Supervised-Learning Algorithm for Large, Multilayered Neural Networks},
  year            = 1993,
  booktitle       = {Neural Networks, 1993., IEEE International Conference on},
  pages           = {778-782 vol.2},
  doi             = {10.1109/ICNN.1993.298654},
  url             = {https://doi.org/10.1109/ICNN.1993.298654},
  keywords        = {feedforward neural nets;genetic algorithms;learning (artificial intelligence);GenLearn;fast supervised-learning
                  algorithm;generalized delta rule;genetic-algorithm techniques;globally-optimal internal representation;local minima;most
                  fit hidden neurons;multilayered neural networks;neural net training;three-layered neural net;weight matrix;Artificial
                  intelligence;Artificial neural networks;Backpropagation algorithms;Feedforward neural networks;Genetic
                  algorithms;Learning;Multi-layer neural network;Neural networks;Neurons;Testing},
  timestamp       = {20181201T1030}
}

@Article{prakash2018-deflecting,
  author          = {Aaditya Prakash and Nick Moran and Solomon Garber and Antonella DiLillo and James A. Storer},
  title           = {Deflecting Adversarial Attacks With Pixel Deflection},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1801.08926},
  eprint          = {1801.08926},
  url             = {http://arxiv.org/abs/1801.08926},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1801-08926},
  keywords        = {adversarial, defense},
  timestamp       = {20181201T1030}
}

@Article{pugh2016-quality,
  author          = {Pugh, Justin K and Soros, Lisa B and Stanley, Kenneth O},
  title           = {Quality Diversity: a New Frontier for Evolutionary Computation},
  journaltitle    = {Frontiers in Robotics and AI},
  year            = 2016,
  volume          = 3,
  pages           = 40,
  journal         = {Frontiers in Robotics and AI},
  publisher       = {Frontiers},
  timestamp       = {20181201T0955}
}

@Article{puskorius1994-neurocontrol,
  author          = {Puskorius, Gintaras V and Feldkamp, Lee A},
  title           = {Neurocontrol of Nonlinear Dynamical Systems With Kalman Filter Trained Recurrent Networks},
  journaltitle    = {IEEE Transactions on neural networks},
  year            = 1994,
  volume          = 5,
  number          = 2,
  pages           = {279--297},
  journal         = {IEEE Transactions on neural networks},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{qian1999-momentum,
  author          = {Qian, Ning},
  title           = {On the Momentum Term in Gradient Descent Learning Algorithms},
  journaltitle    = {Neural networks},
  year            = 1999,
  volume          = 12,
  number          = 1,
  pages           = {145--151},
  journal         = {Neural networks},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{qian2018-analyzing,
  author          = {Qian, Chao and Yu, Yang and Zhou, Zhi-Hua},
  title           = {Analyzing Evolutionary Optimization in Noisy Environments},
  journaltitle    = {Evolutionary Computation},
  year            = 2018,
  volume          = 26,
  number          = 1,
  pages           = {1-41},
  note            = {PMID: 26485581},
  doi             = {10.1162/evco\_a\_00170},
  eprint          = {https://doi.org/10.1162/evco_a_00170},
  url             = {https://doi.org/10.1162/evco\_a\_00170},
  journal         = {Evolutionary Computation},
  timestamp       = {20181201T1030}
}

@InProceedings{qiao2018-new,
  author          = {Chao Qiao and Bo Huang and Guocheng Niu and Daren Li and Daxiang Dong and Wei He and Dianhai Yu and Hua Wu},
  title           = {A New Method of Region Embedding for Text Classification},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BkSDMA36Z},
  timestamp       = {20181201T1030}
}

@Article{qin2010-letor,
  author          = {Qin, Tao and Liu, Tie-Yan and Xu, Jun and Li, Hang},
  title           = {Letor: a Benchmark Collection for Research on Learning To Rank for Information Retrieval},
  journaltitle    = {Information Retrieval},
  year            = 2010,
  volume          = 13,
  number          = 4,
  pages           = {346--374},
  journal         = {Information Retrieval},
  keywords        = {letor},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@InProceedings{rad2017-bb8,
  author          = {Rad, Mahdi and Lepetit, Vincent},
  title           = {BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects
                  without Using Depth},
  year            = 2017,
  booktitle       = {International Conference on Computer Vision},
  volume          = 1,
  number          = 4,
  pages           = 5,
  timestamp       = {20181206T1301}
}

@Article{radford2015-unsupervised,
  author          = {Alec Radford and Luke Metz and Soumith Chintala},
  title           = {Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06434},
  url             = {http://arxiv.org/abs/1511.06434},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/RadfordMC15},
  timestamp       = {20181201T1030}
}

@Article{radford2017-learning,
  author          = {Alec Radford and Rafal J{\'{o}}zefowicz and Ilya Sutskever},
  title           = {Learning To Generate Reviews and Discovering Sentiment},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.01444},
  eprint          = {1704.01444},
  url             = {http://arxiv.org/abs/1704.01444},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/RadfordJS17},
  keywords        = {nlp, unsupervised},
  timestamp       = {20181201T1030}
}

@Article{raghu2016-expressive,
  author          = {{Raghu}, M. and {Poole}, B. and {Kleinberg}, J. and {Ganguli}, S. and {Sohl-Dickstein}, J.},
  title           = {{On the Expressive Power of Deep Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.05336},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InCollection{raghu2017-svcca,
  author          = {Raghu, Maithra and Gilmer, Justin and Yosinski, Jason and Sohl-Dickstein, Jascha},
  title           = {SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {6078--6087},
  url             = {http://papers.nips.cc/paper/7188-svcca-singular-vector-canonical-correlation-analysis-for-deep-learning-dynamics-and-interpretability.pdf},
  keywords        = {svcca},
  timestamp       = {20181201T1030}
}

@Article{rahaman2018-spectral,
  author          = {{Rahaman}, N. and {Arpit}, D. and {Baratin}, A. and {Draxler}, F. and {Lin}, M. and {Hamprecht}, F.~A. and {Bengio},
                  Y. and {Courville}, A.},
  title           = {{On the Spectral Bias of Deep Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jun,
  eprint          = {1806.08734},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180608734R},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Machine Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@InProceedings{rahimi2008-random,
  author          = {Rahimi, Ali and Recht, Benjamin},
  title           = {Random features for large-scale kernel machines},
  year            = 2008,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1177--1184},
  keywords        = {random},
  timestamp       = {20181201T1030}
}

@InProceedings{rahimi2008-uniform,
  author          = {Rahimi, Ali and Recht, Benjamin},
  title           = {Uniform approximation of functions with random bases},
  year            = 2008,
  booktitle       = {Communication, Control, and Computing, 2008 46th Annual Allerton Conference on},
  organization    = {IEEE},
  pages           = {555--561},
  timestamp       = {20181201T1030}
}

@InProceedings{rahimi2009-weighted,
  author          = {Rahimi, Ali and Recht, Benjamin},
  title           = {Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning},
  year            = 2009,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1313--1320},
  timestamp       = {20181201T1030}
}

@InProceedings{rajaraman2001-topic,
  author          = {Rajaraman, Kanagasabi and Tan, Ah-Hwee},
  title           = {Topic Detection, Tracking, and Trend Analysis Using Self-Organizing Neural Networks},
  year            = 2001,
  booktitle       = {Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
  series          = {PAKDD '01},
  publisher       = {Springer-Verlag},
  isbn            = {3-540-41910-1},
  pages           = {102--107},
  url             = {http://dl.acm.org/citation.cfm?id=646419.693501},
  acmid           = 693501,
  address         = {London, UK, UK},
  numpages        = 6,
  timestamp       = {20181201T1030}
}

@Article{rajpurkar2016-squad,
  author          = {Rajpurkar, Pranav and Zhang, Jian and Lopyrev, Konstantin and Liang, Percy},
  title           = {Squad: 100,000+ Questions for Machine Comprehension of Text},
  keywords        = {data, squad},
  journaltitle    = {arXiv preprint arXiv:1606.05250},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1606.05250},
  timestamp       = {20181201T1030}
}

@Article{ramachandran2017-searching,
  author          = {Prajit Ramachandran and Barret Zoph and Quoc V. Le},
  title           = {Searching for Activation Functions},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1710.05941},
  eprint          = {1710.05941},
  url             = {http://arxiv.org/abs/1710.05941},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/abs-1710-05941},
  keywords        = {swish},
  timestamp       = {20181201T1030}
}

@Article{ramesh2018-backpropagation,
  author          = {{Ramesh}, A. and {LeCun}, Y.},
  title           = {{Backpropagation for Implicit Spectral Densities}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jun,
  eprint          = {1806.00499},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180600499R},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{ramesh2018-spectral,
  author          = {{Ramesh}, Aditya and {Choi}, Youngduck and {LeCun}, Yann},
  title           = {{A Spectral Regularizer for Unsupervised Disentanglement}},
  journaltitle    = {arXiv e-prints},
  year            = 2018,
  eid             = {arXiv:1812.01161},
  month           = Dec,
  pages           = {arXiv:1812.01161},
  eprint          = {1812.01161},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/#abs/2018arXiv181201161R},
  archiveprefix   = {arXiv},
  primaryclass    = {stat.ML},
  timestamp       = {20181208T0726}
}

@Article{ranjan2016-hyperface,
  author          = {Rajeev Ranjan and Vishal M. Patel and Rama Chellappa},
  title           = {Hyperface: {A} Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and
                  Gender Recognition},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.01249},
  url             = {http://arxiv.org/abs/1603.01249},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/RanjanPC16},
  timestamp       = {20181201T1030}
}

@InCollection{ranzato2008-sparse,
  author          = {Marc'tesingle aurelio Ranzato and Y-lan Boureau and Yann L. Cun},
  title           = {Sparse Feature Learning for Deep Belief Networks},
  year            = 2008,
  booktitle       = {Advances in Neural Information Processing Systems 20},
  editor          = {J.C. Platt and D. Koller and Y. Singer and S.T. Roweis},
  publisher       = {Curran Associates, Inc.},
  pages           = {1185--1192},
  url             = {http://papers.nips.cc/paper/3363-sparse-feature-learning-for-deep-belief-networks.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{rasmus2015-semi,
  author          = {Rasmus, Antti and Berglund, Mathias and Honkala, Mikko and Valpola, Harri and Raiko, Tapani},
  title           = {Semi-supervised Learning with Ladder Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3546--3554},
  url             = {http://papers.nips.cc/paper/5947-semi-supervised-learning-with-ladder-networks.pdf},
  timestamp       = {20181201T1030}
}

@Book{rasmussen2006-gaussian,
  author          = {Rasmussen, Carl Edward and Williams, Christopher KI},
  title           = {Gaussian processes for machine learning},
  year            = 2006,
  volume          = 1,
  publisher       = {MIT press Cambridge},
  timestamp       = {20181201T1030}
}

@Article{rastegari2016-xnor,
  author          = {Mohammad Rastegari and Vicente Ordonez and Joseph Redmon and Ali Farhadi},
  title           = {Xnor-Net: Imagenet Classification Using Binary Convolutional Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.05279},
  url             = {http://arxiv.org/abs/1603.05279},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/RastegariORF16},
  keywords        = {quantization, xnor, binary},
  timestamp       = {20181201T1030}
}

@Article{ratner2016-data,
  author          = {{Ratner}, A. and {De Sa}, C. and {Wu}, S. and {Selsam}, D. and {R{\'e}}, C.},
  title           = {{Data Programming: Creating Large Training Sets, Quickly}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = may,
  eprint          = {1605.07723},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{rawlinson2007-significance,
  author          = {Rawlinson, Graham},
  title           = {The Significance of Letter Position in Word Recognition},
  keywords        = {brain, linguistic, psycho, scrambled letters},
  journaltitle    = {IEEE Aerospace and Electronic Systems Magazine},
  year            = 2007,
  volume          = 22,
  number          = 1,
  pages           = {26--27},
  journal         = {IEEE Aerospace and Electronic Systems Magazine},
  publisher       = {IEEE},
  timestamp       = {20190106T1041}
}

@InProceedings{rayana2015-collective,
  author          = {Rayana, Shebuti and Akoglu, Leman},
  title           = {Collective opinion spam detection: Bridging review networks and metadata},
  year            = 2015,
  booktitle       = {Proceedings of the 21th acm sigkdd international conference on knowledge discovery and data mining},
  organization    = {ACM},
  pages           = {985--994},
  keywords        = {data, yelp, spam, nyc},
  timestamp       = {20181201T1030}
}

@Article{real2017-large,
  author          = {{Real}, E. and {Moore}, S. and {Selle}, A. and {Saxena}, S. and {Suematsu}, Y.~L. and {Le}, Q. and {Kurakin}, A.},
  title           = {{Large-Scale Evolution of Image Classifiers}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.01041},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {evolution, neural network, nn, genetic},
  timestamp       = {20181201T1030}
}

@InCollection{recasens2015-where,
  author          = {Recasens, Adria and Khosla, Aditya and Vondrick, Carl and Torralba, Antonio},
  title           = {Where are they looking?},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {199--207},
  url             = {http://papers.nips.cc/paper/5848-where-are-they-looking.pdf},
  timestamp       = {20181201T1030}
}

@InProceedings{reddi2018-convergence,
  author          = {Sashank Reddi and Satyen Kale and Sanjiv Kumar},
  title           = {On the Convergence of Adam and Beyond},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  timestamp       = {20190117T1346}
}

@InProceedings{redmon2016-you,
  author          = {Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali},
  title           = {You only look once: Unified, real-time object detection},
  year            = 2016,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {779--788},
  keywords        = {yolo},
  timestamp       = {20181201T1030}
}

@InProceedings{redmon2017-yolo9000,
  author          = {Redmon, Joseph and Farhadi, Ali},
  title           = {Yolo9000: Better, Faster, Stronger},
  year            = 2017,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {7263--7271},
  keywords        = {yolo9000},
  timestamp       = {20181201T1030}
}

@Article{redmon2018-yolov3,
  author          = {Redmon, Joseph and Farhadi, Ali},
  title           = {Yolov3: an Incremental Improvement},
  journaltitle    = {arXiv preprint arXiv:1804.02767},
  year            = 2018,
  journal         = {arXiv preprint arXiv:1804.02767},
  keywords        = {yolo3},
  timestamp       = {20181201T1030}
}

@Article{reed1993-pruning,
  author          = {Reed, Russell},
  title           = {Pruning Algorithms-A Survey},
  journaltitle    = {IEEE transactions on Neural Networks},
  year            = 1993,
  volume          = 4,
  number          = 5,
  pages           = {740--747},
  journal         = {IEEE transactions on Neural Networks},
  keywords        = {pruning, survey},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@InProceedings{reed2014-learning,
  author          = {Reed, Scott and Sohn, Kihyuk and Zhang, Yuting and Lee, Honglak},
  title           = {Learning to disentangle factors of variation with manifold interaction},
  keywords        = {disentangle},
  year            = 2014,
  booktitle       = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
  pages           = {1431--1439},
  timestamp       = {20181201T1030}
}

@InProceedings{reed2015-deep,
  author          = {Reed, Scott E and Zhang, Yi and Zhang, Yuting and Lee, Honglak},
  title           = {Deep visual analogy-making},
  keywords        = {disentangle},
  year            = 2015,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1252--1260},
  timestamp       = {20190109T1618}
}

@Article{reed2016-neural,
  author          = {Reed, Scott and De Freitas, Nando},
  title           = {Neural Programmer-Interpreters},
  journaltitle    = {arXiv preprint arXiv:1511.06279},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1511.06279},
  timestamp       = {20181201T1030}
}

@Article{reimers2017-reporting,
  author          = {Nils Reimers and Iryna Gurevych},
  title           = {Reporting Score Distributions Makes a Difference: Performance Study of Lstm-Networks for Sequence Tagging},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.09861},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InProceedings{reisinger2010-multi,
  author          = {Reisinger, Joseph and Mooney, Raymond J},
  title           = {Multi-prototype vector-space models of word meaning},
  year            = 2010,
  booktitle       = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for
                  Computational Linguistics},
  organization    = {Association for Computational Linguistics},
  pages           = {109--117},
  timestamp       = {20181201T1030}
}

@InProceedings{rek2010-software,
  author          = {Radim {\v R}eh{\r u}{\v r}ek and Petr Sojka},
  title           = {{Software Framework for Topic Modelling with Large Corpora}},
  year            = 2010,
  booktitle       = {{Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks}},
  language        = {English},
  note            = {\url{http://is.muni.cz/publication/884893/en}},
  publisher       = {ELRA},
  month           = May,
  pages           = {45--50},
  address         = {Valletta, Malta},
  day             = 22,
  keywords        = {gensim},
  timestamp       = {20181201T1030}
}

@InCollection{rempis2012-interactively,
  author          = {Rempis, Christian and Pasemann, Frank},
  title           = {An Interactively Constrained Neuro-Evolution Approach for Behavior Control of Complex Robots},
  year            = 2012,
  booktitle       = {Variants of Evolutionary Algorithms for Real-World Applications},
  publisher       = {Springer},
  pages           = {305--341},
  timestamp       = {20181201T1030}
}

@InCollection{ren2015-exploring,
  author          = {Ren, Mengye and Kiros, Ryan and Zemel, Richard},
  title           = {Exploring Models and Data for Image Question Answering},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2953--2961},
  url             = {http://papers.nips.cc/paper/5640-exploring-models-and-data-for-image-question-answering.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{ren2015-faster,
  author          = {Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
  title           = {Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {91--99},
  url             = {http://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdf},
  keywords        = {faster rcnn},
  timestamp       = {20181201T1030}
}

@Article{ricci-tersenghi2009-cavity,
  author          = {Ricci-Tersenghi, Federico and Semerjian, Guilhem},
  title           = {On the Cavity Method for Decimated Random Constraint Satisfaction Problems and the Analysis of Belief Propagation
                  Guided Decimation Algorithms},
  journaltitle    = {Journal of Statistical Mechanics: Theory and Experiment},
  year            = 2009,
  volume          = 2009,
  number          = 09,
  pages           = {P09001},
  journal         = {Journal of Statistical Mechanics: Theory and Experiment},
  publisher       = {IOP Publishing},
  timestamp       = {20181201T1030}
}

@InProceedings{riedmiller1993,
  author          = {Riedmiller, M. and Braun, H.},
  title           = {A direct adaptive method for faster backpropagation learning: the RPROP algorithm},
  year            = 1993,
  booktitle       = {Neural Networks, 1993., IEEE International Conference on},
  pages           = {586-591 vol.1},
  doi             = {10.1109/ICNN.1993.298623},
  url             = {https://doi.org/10.1109/ICNN.1993.298623},
  keywords        = {adaptive systems;backpropagation;feedforward neural nets;RPROP algorithm;direct adaptive method;error function;faster
                  backpropagation learning;gradient decent type;multilayer feedforward networks;neural
                  nets;weight-updates;Acceleration;Backpropagation algorithms;Computer networks;Convergence;Feedforward
                  systems;Neurons;Supervised learning;Writing},
  timestamp       = {20181201T1030}
}

@Article{riedmiller1994-advanced,
  author          = "Martin Riedmiller",
  title           = {Advanced Supervised Learning in Multi-Layer Perceptrons - From Backpropagation To Adaptive Learning Algorithms},
  journaltitle    = "Computer Standards \& Interfaces",
  year            = 1994,
  volume          = 16,
  number          = 3,
  pages           = "265 - 278",
  issn            = "0920-5489",
  doi             = {10.1016/0920-5489(94)90017-5},
  url             = {https://doi.org/10.1016/0920-5489(94)90017-5},
  journal         = "Computer Standards \& Interfaces",
  keywords        = "Supervised learning,Multi-layer perceptrons,Feedforward networks,Adaptive learning algorithms,Benchmark
                  problems,Robustness",
  timestamp       = {20181201T1030}
}

@InProceedings{rifai2011-contractive,
  author          = {Rifai, Salah and Vincent, Pascal and Muller, Xavier and Glorot, Xavier and Bengio, Yoshua},
  title           = {Contractive auto-encoders: Explicit invariance during feature extraction},
  year            = 2011,
  booktitle       = {Proceedings of the 28th international conference on machine learning (ICML-11)},
  pages           = {833--840},
  timestamp       = {20181201T1030}
}

@InProceedings{ringel2018-critical,
  author          = {Zohar Ringel and Rodrigo Andrade de Bem},
  title           = {Critical Percolation as a Framework to Analyze the Training of Deep Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BJGWO9k0Z},
  timestamp       = {20181201T1030}
}

@InCollection{rippel2015-spectral,
  author          = {Rippel, Oren and Snoek, Jasper and Adams, Ryan P},
  title           = {Spectral Representations for Convolutional Neural Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2449--2457},
  url             = {http://papers.nips.cc/paper/5649-spectral-representations-for-convolutional-neural-networks.pdf},
  timestamp       = {20181201T1030}
}

@Article{rissanen1978-modeling,
  author          = {Rissanen, Jorma},
  title           = {Modeling By Shortest Data Description},
  journaltitle    = {Automatica},
  year            = 1978,
  volume          = 14,
  number          = 5,
  pages           = {465--471},
  journal         = {Automatica},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{rissanen1986-stochastic,
  author          = {Rissanen, Jorma},
  title           = {Stochastic Complexity and Modeling},
  journaltitle    = {The annals of statistics},
  year            = 1986,
  pages           = {1080--1100},
  journal         = {The annals of statistics},
  publisher       = {JSTOR},
  timestamp       = {20181201T1030}
}

@Article{rivoire2004-properties,
  author          = {Rivoire, Olivier},
  title           = {Properties of Atypical Graphs From Negative Complexities},
  journaltitle    = {Journal of statistical physics},
  year            = 2004,
  volume          = 117,
  number          = 3,
  pages           = {453--476},
  journal         = {Journal of statistical physics},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Book{robbins2009-cambridge,
  author          = {Robbins, Philip and Aydede, Murat},
  title           = {The Cambridge handbook of situated cognition},
  year            = 2009,
  publisher       = {Cambridge University Press Cambridge},
  timestamp       = {20181201T1030}
}

@Book{rockafellar2015-convex,
  author          = {Rockafellar, Ralph Tyrell},
  title           = {Convex analysis},
  year            = 2015,
  publisher       = {Princeton university press},
  timestamp       = {20181201T1030}
}

@Article{rocktaeschel2015-reasoning,
  author          = {Tim Rockt{\"a}schel and Edward Grefenstette and Karl Moritz Hermann and Tom{\'a}{\v{s}} Ko{\v{c}}isk{\'y} and Phil
                  Blunsom},
  title           = {Reasoning About Entailment With Neural Attention},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1509.06664},
  url             = {http://arxiv.org/abs/1509.06664},
  journal         = {CoRR},
  keywords        = {qa, lstm},
  timestamp       = {20181201T1030}
}

@Article{rodriguez1999-recurrent,
  author          = {Paul Rodriguez and Janet Wiles and Jeffrey L Elman},
  title           = {A Recurrent Neural Network That Learns To Count},
  journaltitle    = {Connection Science},
  year            = 1999,
  volume          = 11,
  number          = 1,
  pages           = {5-40},
  doi             = {10.1080/095400999116340},
  eprint          = {http://dx.doi.org/10.1080/095400999116340},
  url             = {https://doi.org/10.1080/095400999116340},
  journal         = {Connection Science},
  timestamp       = {20181201T1030}
}

@Article{roelfsema2005-attention,
  author          = {Roelfsema, Pieter R and van Ooyen, Arjen},
  title           = {Attention-Gated Reinforcement Learning of Internal Representations for Classification},
  journaltitle    = {Neural computation},
  year            = 2005,
  volume          = 17,
  number          = 10,
  pages           = {2176--2214},
  journal         = {Neural computation},
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@InProceedings{rolnick2018-power,
  author          = {David Rolnick and Max Tegmark},
  title           = {The Power of Deeper Networks for Expressing Natural Functions},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SyProzZAW},
  timestamp       = {20181201T1030}
}

@InProceedings{romera-paredes2015,
  author          = {Romera-Paredes, Bernardino and Torr, PHS},
  title           = {An embarrassingly simple approach to zero-shot learning},
  year            = 2015,
  booktitle       = {Proceedings of The 32nd International Conference on Machine Learning},
  pages           = {2152--2161},
  timestamp       = {20181201T1030}
}

@Article{romero2014-fitnets,
  author          = {Adriana Romero and Nicolas Ballas and Samira Ebrahimi Kahou and Antoine Chassang and Carlo Gatta and Yoshua Bengio},
  title           = {Fitnets: Hints for Thin Deep Nets},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6550},
  url             = {http://arxiv.org/abs/1412.6550},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/RomeroBKCGB14},
  timestamp       = {20181201T1030}
}

@Article{rosca2017-variational,
  author          = {Rosca, Mihaela and Lakshminarayanan, Balaji and Warde-Farley, David and Mohamed, Shakir},
  title           = {Variational Approaches for Auto-Encoding Generative Adversarial Networks},
  journaltitle    = {arXiv preprint arXiv:1706.04987},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1706.04987},
  timestamp       = {20181201T1030}
}

@InCollection{rosenbaum2015-return,
  author          = {Rosenbaum, Dan and Weiss, Yair},
  title           = {The Return of the Gating Network: Combining Generative Models and Discriminative Training in Natural Image Priors},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2683--2691},
  url             = {http://papers.nips.cc/paper/5853-the-return-of-the-gating-network-combining-generative-models-and-discriminative-training-in-natural-image-priors.pdf},
  timestamp       = {20181201T1030}
}

@Article{rosenfeld2018-elephant,
  author          = {{Rosenfeld}, A. and {Zemel}, R. and {Tsotsos}, J.~K.},
  title           = {{The Elephant in the Room}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.03305},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180803305R},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{rozsa2016-adversarial,
  author          = {Andras Rozsa and Ethan M. Rudd and Terrance E. Boult},
  title           = {Adversarial Diversity and Hard Positive Generation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1605.01775},
  journal         = {CoRR},
  keywords        = {adversarial, defense, pass score},
  timestamp       = {20181201T1030}
}

@Article{rozsa2016-towards,
  author          = {Andras Rozsa and Manuel G{\"{u}}nther and Terrance E. Boult},
  title           = {Towards Robust Deep Neural Networks With {BANG}},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.00138},
  journal         = {CoRR},
  keywords        = {adversarial},
  timestamp       = {20181201T1030}
}

@Article{rozsa2017-adversarial,
  author          = {Rozsa, Andras and G{\"u}nther, Manuel and Boult, Terrance E},
  title           = {Adversarial Robustness: Softmax Versus Openmax},
  journaltitle    = {arXiv preprint arXiv:1708.01697},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1708.01697},
  keywords        = {adversarial},
  timestamp       = {20181201T1030}
}

@Article{rubenstein1965-contextual,
  author          = {Rubenstein, Herbert and Goodenough, John B},
  title           = {Contextual Correlates of Synonymy},
  journaltitle    = {Communications of the ACM},
  year            = 1965,
  volume          = 8,
  number          = 10,
  pages           = {627--633},
  journal         = {Communications of the ACM},
  keywords        = {rg},
  publisher       = {ACM},
  timestamp       = {20181201T1030}
}

@Article{rubner2000-earth,
  author          = {Rubner, Yossi and Tomasi, Carlo and Guibas, Leonidas J},
  title           = {The Earth Mover's Distance As a Metric for Image Retrieval},
  journaltitle    = {International journal of computer vision},
  year            = 2000,
  volume          = 40,
  number          = 2,
  pages           = {99--121},
  journal         = {International journal of computer vision},
  keywords        = {emd},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{ruder2017-overview,
  author          = {Sebastian Ruder},
  title           = {An Overview of Multi-Task Learning in Deep Neural Networks},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.05098},
  eprint          = {1706.05098},
  url             = {http://arxiv.org/abs/1706.05098},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/Ruder17a},
  keywords        = {survey, mtl, multi-task, join-learning, learning-to-learn},
  timestamp       = {20181201T1030}
}

@Article{rueckle2018-concatenated,
  author          = {Andreas R{\"u}ckl{\'e} and Steffen Eger and Maxime Peyrard and Iryna Gurevych},
  title           = {Concatenated P-Mean Word Embeddings As Universal Cross-Lingual Sentence Representations},
  keywords        = {embedding, sentence},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1803.01400},
  eprint          = {1803.01400},
  url             = {http://arxiv.org/abs/1803.01400},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1803-01400},
  timestamp       = {20190103T1609}
}

@Article{rumelhart1986-learning,
  author          = {Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J},
  title           = {Learning Representations By Back-Propagating Errors},
  keywords        = {backprop},
  journaltitle    = {nature},
  year            = 1986,
  volume          = 323,
  number          = 6088,
  pages           = 533,
  journal         = {nature},
  publisher       = {Nature Publishing Group},
  timestamp       = {20190207T1353}
}

@Manual{russ2017-quantitave,
  author          = {Russ Salakhutdinov, Yuhuai Wu, Yuri Burda, Roger Grosse},
  title           = {On the Quantitave Evaluation of Deep Generatve Models},
  year            = 2017,
  url             = {http://www.cs.cmu.edu/~rsalakhu/talk_Eval.pdf},
  timestamp       = {20181201T1030}
}

@Article{russakovsky2015-imagenet,
  author          = {Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng
                  and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and others},
  title           = {Imagenet Large Scale Visual Recognition Challenge},
  journaltitle    = {International Journal of Computer Vision},
  year            = 2015,
  volume          = 115,
  number          = 3,
  pages           = {211--252},
  journal         = {International Journal of Computer Vision},
  publisher       = {Springer},
  timestamp       = {20190130T1627}
}

@Article{rusu2016-progressive,
  author          = {Rusu, Andrei A and Rabinowitz, Neil C and Desjardins, Guillaume and Soyer, Hubert and Kirkpatrick, James and
                  Kavukcuoglu, Koray and Pascanu, Razvan and Hadsell, Raia},
  title           = {Progressive Neural Networks},
  journaltitle    = {arXiv preprint arXiv:1606.04671},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1606.04671},
  keywords        = {transfer learning},
  timestamp       = {20181201T1030}
}

@Article{saad1990-learning,
  author          = {Saad, D and Marom, E},
  title           = {Learning By Choice of Internal Representations: an Energy Minimization Approach},
  journaltitle    = {Complex systems},
  year            = 1990,
  volume          = 4,
  number          = 1,
  pages           = {107--118},
  journal         = {Complex systems},
  publisher       = {Complex Systems Publications, Incorporated},
  timestamp       = {20181201T1030}
}

@Article{saad1990-training,
  author          = {Saad, D and Marom, E},
  title           = {Training Feed Forward Nets With Binary Weights Via a Modified Chir Algorithm},
  journaltitle    = {Complex Systems},
  year            = 1990,
  volume          = 4,
  pages           = {573--586},
  journal         = {Complex Systems},
  keywords        = {quantization, binary, chir},
  timestamp       = {20181201T1030}
}

@Article{sabour2015-adversarial,
  author          = {Sabour, Sara and Cao, Yanshuai and Faghri, Fartash and Fleet, David J},
  title           = {Adversarial Manipulation of Deep Representations},
  journaltitle    = {arXiv preprint arXiv:1511.05122},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1511.05122},
  timestamp       = {20181201T1030}
}

@Article{sabour2017-dynamic,
  author          = {{Sabour}, S. and {Frosst}, N. and {E Hinton}, G.},
  title           = {{Dynamic Routing Between Capsules}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.09829},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171009829S},
  archiveprefix   = "arXiv",
  keywords        = {capsule},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{sagun2014-explorations,
  author          = {{Sagun}, L. and {Ugur Guney}, V. and {Ben Arous}, G. and {LeCun}, Y.},
  title           = {{Explorations on High Dimensional landscapes}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = dec,
  eprint          = {1412.6615},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2014arXiv1412.6615S},
  archiveprefix   = "arXiv",
  keywords        = {theory, spin glass},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{sagun2016-singularity,
  author          = {Levent Sagun and L{\'{e}}on Bottou and Yann LeCun},
  title           = {Singularity of the Hessian in Deep Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.07476},
  eprint          = {1611.07476},
  url             = {http://arxiv.org/abs/1611.07476},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/SagunBL16},
  keywords        = {hessian, eigenvalue},
  timestamp       = {20181201T1030}
}

@Article{sagun2017-empirical,
  author          = {{Sagun}, L. and {Evci}, U. and {Ugur Guney}, V. and {Dauphin}, Y. and {Bottou}, L.},
  title           = {{Empirical Analysis of the Hessian of Over-Parametrized Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.04454},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@InProceedings{saito2015-illustration2vec,
  author          = {Saito, Masaki and Matsui, Yusuke},
  title           = {Illustration2Vec: A Semantic Vector Representation of Illustrations},
  year            = 2015,
  booktitle       = {SIGGRAPH Asia Technical Briefs},
  timestamp       = {20181201T1030}
}

@InProceedings{sak2014-long,
  author          = {Sak, Ha{\c{s}}im and Senior, Andrew and Beaufays, Fran{\c{c}}oise},
  title           = {Long short-term memory recurrent neural network architectures for large scale acoustic modeling},
  year            = 2014,
  booktitle       = {Fifteenth Annual Conference of the International Speech Communication Association},
  timestamp       = {20181201T1029}
}

@InProceedings{salakhutdinov2007-restricted,
  author          = {Ruslan Salakhutdinov and Andriy Mnih and Geoffrey Hinton},
  title           = {Restricted Boltzmann machines for collaborative filtering},
  year            = 2007,
  booktitle       = {In Machine Learning, Proceedings of the Twenty-fourth International Conference (ICML 2004). ACM},
  publisher       = {AAAI Press},
  pages           = {791--798},
  timestamp       = {20181201T1030}
}

@Article{salimans2016-improved,
  author          = {{Salimans}, T. and {Goodfellow}, I. and {Zaremba}, W. and {Cheung}, V. and {Radford}, A. and {Chen}, X.},
  title           = {{Improved Techniques for Training GANs}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.03498},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {gan, inception score, IS},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{salimans2017-evolution,
  author          = {{Salimans}, T. and {Ho}, J. and {Chen}, X. and {Sutskever}, I.},
  title           = {{Evolution Strategies As a Scalable Alternative To Reinforcement Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.03864},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Learning, Computer
                  Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML",
  timestamp       = {20181201T1030}
}

@Article{samangouei2018-defense,
  author          = {{Samangouei}, P. and {Kabkab}, M. and {Chellappa}, R.},
  title           = {{Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = may,
  eprint          = {1805.06605},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180506605S},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.CV",
  timestamp       = {20181201T1030}
}

@Article{samanta2017-towards,
  author          = {Samanta, Suranjana and Mehta, Sameep},
  title           = {Towards Crafting Text Adversarial Samples},
  journaltitle    = {arXiv preprint arXiv:1707.02812},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1707.02812},
  keywords        = {adversarial, text, imdb, twitter, cnn, classification},
  timestamp       = {20181201T1030}
}

@Article{sandholm2015-solving,
  author          = {Sandholm, Tuomas},
  title           = {Solving Imperfect-Information Games},
  journaltitle    = {Science},
  year            = 2015,
  volume          = 347,
  number          = 6218,
  pages           = {122--123},
  journal         = {Science},
  publisher       = {American Association for the Advancement of Science},
  timestamp       = {20181201T1030}
}

@Article{santana2016-learning,
  author          = {Eder Santana and George Hotz},
  title           = {Learning a Driving Simulator},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1608.01230},
  url             = {http://arxiv.org/abs/1608.01230},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SantanaH16},
  timestamp       = {20181201T1030}
}

@InProceedings{santoro2016-meta,
  author          = {Santoro, Adam and Bartunov, Sergey and Botvinick, Matthew and Wierstra, Daan and Lillicrap, Timothy},
  title           = {Meta-learning with memory-augmented neural networks},
  year            = 2016,
  booktitle       = {International conference on machine learning},
  pages           = {1842--1850},
  keywords        = {meta learning},
  timestamp       = {20181201T1030}
}

@Article{santoro2016-one,
  author          = {Adam Santoro and Sergey Bartunov and Matthew Botvinick and Daan Wierstra and Timothy P. Lillicrap},
  title           = {One-Shot Learning With Memory-Augmented Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1605.06065},
  url             = {http://arxiv.org/abs/1605.06065},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SantoroBBWL16},
  timestamp       = {20181201T1030}
}

@Article{santoro2017-simple,
  author          = {{Santoro}, A. and {Raposo}, D. and {Barrett}, D.~G.~T. and {Malinowski}, M. and {Pascanu}, R. and {Battaglia}, P. and
                  {Lillicrap}, T.},
  title           = {{A Simple Neural Network Module for Relational reasoning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.01427},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Learning},
  primaryclass    = "cs.CL",
  timestamp       = {20181201T1030}
}

@InProceedings{satorras2018-few,
  author          = {Victor Garcia Satorras and Joan Bruna Estrach},
  title           = {Few-Shot Learning with Graph Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BJj6qGbRW},
  timestamp       = {20181201T1030}
}

@InProceedings{saxe2011-random,
  author          = {Saxe, Andrew and Koh, Pang W and Chen, Zhenghao and Bhand, Maneesh and Suresh, Bipin and Ng, Andrew Y},
  title           = {On Random Weights and Unsupervised Feature Learning},
  year            = 2011,
  booktitle       = {Proceedings of the 28th international conference on machine learning (ICML-11)},
  pages           = {1089--1096},
  keywords        = {random, architecture},
  timestamp       = {20181201T1030}
}

@InProceedings{saxe2018-information,
  author          = {Andrew Michael Saxe and Yamini Bansal and Joel Dapello and Madhu Advani and Artemy Kolchinsky and Brendan Daniel Tracey
                  and David Daniel Cox},
  title           = {On the Information Bottleneck Theory of Deep Learning},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=ry_WPG-A-},
  timestamp       = {20181201T1030}
}

@InCollection{scalettar1988-emergence,
  author          = {Scalettar, R. and Zee, A.},
  title           = {Emergence of Grandmother Memory in Feed Forward Networks: Learning with Noise and Forgetfulness},
  year            = 1988,
  booktitle       = {Connectionist Models and Their Implications: Readings from Cognitive Science},
  editor          = {Waltz, David and Feldman, Jerome A.},
  publisher       = {Ablex Publishing Corp.},
  isbn            = {0-89391-456-8},
  pages           = {309--327},
  url             = {http://dl.acm.org/citation.cfm?id=54455.54466},
  acmid           = 54466,
  address         = {Norwood, NJ, USA},
  numpages        = 19,
  timestamp       = {20181201T1030}
}

@Article{scarselli2009-graph,
  author          = {Scarselli, Franco and Gori, Marco and Tsoi, Ah Chung and Hagenbuchner, Markus and Monfardini, Gabriele},
  title           = {The Graph Neural Network Model},
  journaltitle    = {IEEE Transactions on Neural Networks},
  year            = 2009,
  volume          = 20,
  number          = 1,
  pages           = {61--80},
  journal         = {IEEE Transactions on Neural Networks},
  publisher       = {IEEE},
  timestamp       = {20181201T1030}
}

@Article{scellier2016-equilibrium,
  author          = {Benjamin Scellier and Yoshua Bengio},
  title           = {Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.05179},
  url             = {http://arxiv.org/abs/1602.05179},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ScellierB16},
  timestamp       = {20181201T1030}
}

@Article{scellier2017-equivalence,
  author          = {{Scellier}, B. and {Bengio}, Y.},
  title           = {{Equivalence of Equilibrium Propagation and Recurrent Backpropagation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = nov,
  eprint          = {1711.08416},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171108416S},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG",
  timestamp       = {20181201T1030}
}

@Article{scellier2018-extending,
  author          = {Scellier, Benjamin and Goyal, Anirudh and Binas, Jonathan and Mesnard, Thomas and Bengio, Yoshua},
  title           = {Extending the Framework of Equilibrium Propagation To General Dynamics},
  journaltitle    = {ICLR Review},
  year            = 2018,
  journal         = {ILCR Review},
  timestamp       = {20181201T1030}
}

@Article{schapire1990-strength,
  author          = {Schapire, Robert E},
  title           = {The Strength of Weak Learnability},
  journaltitle    = {Machine learning},
  year            = 1990,
  volume          = 5,
  number          = 2,
  pages           = {197--227},
  journal         = {Machine learning},
  publisher       = {Springer},
  timestamp       = {20181201T1030}
}

@Article{schaul2015-prioritized,
  author          = {Tom Schaul and John Quan and Ioannis Antonoglou and David Silver},
  title           = {Prioritized Experience Replay},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.05952},
  journal         = {CoRR},
  timestamp       = {20181201T1030}
}

@InCollection{schiffmann1990-performance,
  author          = {Schiffmann, Wolfram and Joost, Merten and Werner, Randolf},
  title           = {Performance evaluation of evolutionarily created neural network topologies},
  year            = 1990,
  booktitle       = {Parallel Problem Solving from Nature},
  publisher       = {Springer},
  pages           = {274--283},
  timestamp       = {20181201T1030}
}

@InProceedings{schiffmann1993-application,
  author          = {Schiffmann, Wolfram and Joost, Merten and Werner, Randolf},
  title           = {Application of genetic algorithms to the construction of topologies for multilayer perceptrons},
  year            = 1993,
  booktitle       = {Artificial Neural Nets and Genetic Algorithms},
  organization    = {Springer},
  pages           = {675--682},
  timestamp       = {20181201T1030}
}

@Article{schiller2005-analyzing,
  author          = {Schiller, Ulf D and Steil, Jochen J},
  title           = {Analyzing the Weight Dynamics of Recurrent Learning Algorithms},
  journaltitle    = {Neurocomputing},
  year            = 2005,
  volume          = 63,
  pages           = {5--23},
  journal         = {Neurocomputing},
  keywords        = {atiya-parlos recurrent learning, aprl},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@InProceedings{schleimer2003-winnowing,
  author          = {Schleimer, Saul and Wilkerson, Daniel S and Aiken, Alex},
  title           = {Winnowing: Local Algorithms for Document Fingerprinting},
  year            = 2003,
  booktitle       = {Proceedings of the 2003 ACM SIGMOD international conference on Management of data},
  organization    = {ACM},
  pages           = {76--85},
  timestamp       = {20181201T1030}
}

@InCollection{schmah2009-generative,
  author          = {Tanya Schmah and Geoffrey E. Hinton and Steven L. Small and Stephen Strother and Richard S. Zemel},
  title           = {Generative versus discriminative training of RBMs for classification of fMRI images},
  year            = 2009,
  booktitle       = {Advances in Neural Information Processing Systems 21},
  editor          = {D. Koller and D. Schuurmans and Y. Bengio and L. Bottou},
  publisher       = {Curran Associates, Inc.},
  pages           = {1409--1416},
  url             = {http://papers.nips.cc/paper/3577-generative-versus-discriminative-training-of-rbms-for-classification-of-fmri-images.pdf},
  timestamp       = {20181201T1030}
}

@InCollection{schmid2015-comparing,
  author          = {Schmid, Ute and Ragni, Marco},
  title           = {Comparing Computer Models Solving Number Series Problems},
  year            = 2015,
  booktitle       = {Artificial General Intelligence},
  publisher       = {Springer},
  pages           = {352--361},
  timestamp       = {20181201T1030}
}

@Misc{schmidhuber1996-guessing,
  author          = {Schmidhuber, Juergen and Hochreiter, Sepp},
  title           = {Guessing Can Outperform Many Long Time Lag Algorithms},
  year            = 1996,
  publisher       = {Citeseer},
  timestamp       = {20181201T1030}
}

@Article{schmidhuber1997-discovering,
  author          = {Schmidhuber, J{\"u}rgen},
  title           = {Discovering Neural Nets With Low Kolmogorov Complexity and High Generalization Capability},
  journaltitle    = {Neural Networks},
  year            = 1997,
  volume          = 10,
  number          = 5,
  pages           = {857--873},
  journal         = {Neural Networks},
  keywords        = {flat minima},
  publisher       = {Elsevier},
  timestamp       = {20181201T1030}
}

@Article{schmidhuber2001-evaluating,
  author          = {Schmidhuber, J{\"u}rgen and Hochreiter, S and Bengio, Y},
  title           = {Evaluating Benchmark Problems By Random Guessing},
  journaltitle    = {A Field Guide to Dynamical Recurrent Networks, ed. J. Kolen and S. Cremer},
  year            = 2001,
  pages           = {231--235},
  journal         = {A Field Guide to Dynamical Recurrent Networks, ed. J. Kolen and S. Cremer},
  timestamp       = {20181201T1030}
}

@Article{schmidhuber2007-training,
  author          = {Schmidhuber, J{\"u}rgen and Wierstra, Daan and Gagliolo, Matteo and Gomez, Faustino},
  title           = {Training Recurrent Networks By Evolino},
  journaltitle    = {Neural Comput.},
  year            = 2007,
  volume          = 19,
  number          = 3,
  month           = mar,
  pages           = {757--779},
  issn            = {0899-7667},
  doi             = {10.1162/neco.2007.19.3.757},
  url             = {https://doi.org/10.1162/neco.2007.19.3.757},
  journal         = {Neural Comput.},
  acmid           = 1246956,
  address         = {Cambridge, MA, USA},
  issue_date      = {March 2007},
  numpages        = 23,
  publisher       = {MIT Press},
  timestamp       = {20181201T1030}
}

@Article{schmidhuber2012-self,
  author          = {J{\"u}rgen Schmidhuber},
  title           = {Self-Delimiting Neural Networks},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1210.0118},
  url             = {http://arxiv.org/abs/1210.0118},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1210-0118},
  timestamp       = {20181201T1030}
}

@Article{schmidhuber2018-one,
  author          = {{Schmidhuber}, J.},
  title           = {{One Big Net for Everything}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.08864},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180208864S},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence},
  primaryclass    = "cs.AI",
  timestamp       = {20181201T1030}
}

@InProceedings{schmidt1992-feedforward,
  author          = {Schmidt, Wouter F and Kraaijveld, Martin A and Duin, Robert PW},
  title           = {Feedforward neural networks with random weights},
  year            = 1992,
  booktitle       = {Pattern Recognition, 1992. Vol. II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR
                  International Conference on},
  organization    = {IEEE},
  pages           = {1--4},
  timestamp       = {20181201T1030}
}

@InBook{schoelkopf2007-efficient,
  title           = {Efficient Learning of Sparse Representations with an Energy-Based Model},
  year            = 2007,
  author          = {Sch{\"o}lkopf, B. and Platt, J. and Hofmann, T.},
  booktitle       = {Advances in Neural Information Processing Systems 19:Proceedings of the 2006 Conference},
  publisher       = {MIT Press},
  isbn            = 9780262256919,
  pages           = {1137-1144},
  url             = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6287442},
  timestamp       = {20181209T1216}
}

@Article{schoenemann1966-generalized,
  author          = {Sch{\"o}nemann, Peter H},
  title           = {A Generalized Solution of the Orthogonal Procrustes Problem},
  journaltitle    = {Psychometrika},
  year            = 1966,
  volume          = 31,
  number          = 1,
  pages           = {1--10},
  journal         = {Psychometrika},
  publisher       = {Springer},
  timestamp       = {20181229T1014}
}

@Article{schuetze1998-automatic,
  author          = {Sch{\"u}tze, Hinrich},
  title           = {Automatic Word Sense Discrimination},
  journaltitle    = {Computational linguistics},
  year            = 1998,
  volume          = 24,
  number          = 1,
  pages           = {97--123},
  keywords        = {word sense discovery, wsd},
  journal         = {Computational linguistics},
  publisher       = {MIT Press}
}

@Article{schulman2015-gradient,
  author          = {John Schulman and Nicolas Heess and Theophane Weber and Pieter Abbeel},
  title           = {Gradient Estimation Using Stochastic Computation Graphs},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.05254},
  url             = {http://arxiv.org/abs/1506.05254},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SchulmanHWA15},
  timestamp       = {Wed, 01 Jul 2015 15:10:24 +0200}
}

@Article{schulman2015-high,
  author          = {John Schulman and Philipp Moritz and Sergey Levine and Michael I. Jordan and Pieter Abbeel},
  title           = {High-Dimensional Continuous Control Using Generalized Advantage Estimation},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.02438},
  url             = {http://arxiv.org/abs/1506.02438},
  keywords        = {rl, pg, gae, policy gradient},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SchulmanMLJA15},
  timestamp       = {Wed, 01 Jul 2015 15:10:24 +0200}
}

@Article{schulman2015-trust,
  author          = {John Schulman and Sergey Levine and Philipp Moritz and Michael I. Jordan and Pieter Abbeel},
  title           = {Trust Region Policy Optimization},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1502.05477},
  eprint          = {1502.05477},
  url             = {http://arxiv.org/abs/1502.05477},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/SchulmanLMJA15},
  timestamp       = {Mon, 13 Aug 2018 16:48:08 +0200}
}

@Article{schulman2017-proximal,
  author          = {Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg},
  title           = {Proximal Policy Optimization Algorithms},
  journaltitle    = {arXiv preprint arXiv:1707.06347},
  year            = 2017,
  keywords        = {rl, ppg},
  journal         = {arXiv preprint arXiv:1707.06347}
}

@Article{schuster1997-bidirectional,
  author          = {Schuster, Mike and Paliwal, Kuldip K},
  title           = {Bidirectional Recurrent Neural Networks},
  journaltitle    = {IEEE Transactions on Signal Processing},
  year            = 1997,
  volume          = 45,
  number          = 11,
  pages           = {2673--2681},
  journal         = {IEEE Transactions on Signal Processing},
  publisher       = {IEEE}
}

@InProceedings{schuster2012-japanese,
  author          = {Schuster, Mike and Nakajima, Kaisuke},
  title           = {Japanese and korean voice search},
  year            = 2012,
  booktitle       = {Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on},
  organization    = {IEEE},
  pages           = {5149--5152}
}

@Article{schwartz2008-introduction,
  author          = {Schwartz, Matthew},
  title           = {Introduction To Quantum Field Theory},
  journaltitle    = {Harvard University},
  year            = 2008,
  journal         = {Harvard University}
}

@Article{schwenk2000-boosting,
  author          = {Schwenk, Holger and Bengio, Yoshua},
  title           = {Boosting Neural Networks},
  journaltitle    = {Neural Computation},
  year            = 2000,
  volume          = 12,
  number          = 8,
  pages           = {1869--1887},
  journal         = {Neural Computation},
  publisher       = {MIT Press}
}

@InProceedings{sculley2014-machine,
  author          = {D. Sculley and Gary Holt and Daniel Golovin and Eugene Davydov and Todd Phillips and Dietmar Ebner and Vinay Chaudhary
                  and Michael Young},
  title           = {Machine Learning: The High Interest Credit Card of Technical Debt},
  year            = 2014,
  booktitle       = {SE4ML: Software Engineering for Machine Learning (NIPS 2014 Workshop)}
}

@InCollection{sculley2015-hidden,
  author          = {Sculley, D. and Holt, Gary and Golovin, Daniel and Davydov, Eugene and Phillips, Todd and Ebner, Dietmar and Chaudhary,
                  Vinay and Young, Michael and Crespo, Jean-Fran{\cc}ois and Dennison, Dan},
  title           = {Hidden Technical Debt in Machine Learning Systems},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2503--2511},
  url             = {http://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems.pdf}
}

@InProceedings{secretan2008-picbreeder,
  author          = {Secretan, Jimmy and Beato, Nicholas and D Ambrosio, David B and Rodriguez, Adelein and Campbell, Adam and Stanley,
                  Kenneth O},
  title           = {Picbreeder: evolving pictures collaboratively online},
  year            = 2008,
  booktitle       = {Proceedings of the SIGCHI Conference on Human Factors in Computing Systems},
  organization    = {ACM},
  pages           = {1759--1768}
}

@Article{see2016-compression,
  author          = {See, Abigail and Luong, Minh-Thang and Manning, Christopher D},
  title           = {Compression of Neural Machine Translation Models Via Pruning},
  journaltitle    = {arXiv preprint arXiv:1606.09274},
  year            = 2016,
  keywords        = {compression, lstm, nlp, nmt, pruning, ende},
  journal         = {arXiv preprint arXiv:1606.09274}
}

@Article{sehnke2010-parameter,
  author          = {Sehnke, Frank and Osendorfer, Christian and R{\"u}ckstie{\ss}, Thomas and Graves, Alex and Peters, Jan and Schmidhuber,
                  J{\"u}rgen},
  title           = {Parameter-Exploring Policy Gradients},
  journaltitle    = {Neural Networks},
  year            = 2010,
  volume          = 23,
  number          = 4,
  pages           = {551--559},
  keywords        = {pepg},
  journal         = {Neural Networks},
  publisher       = {Elsevier}
}

@InProceedings{seide2014-bit,
  author          = {Seide, Frank and Fu, Hao and Droppo, Jasha and Li, Gang and Yu, Dong},
  title           = {1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs},
  year            = 2014,
  booktitle       = {Interspeech 2014},
  month           = {September},
  url             =
                  {https://www.microsoft.com/en-us/research/publication/1-bit-stochastic-gradient-descent-and-application-to-data-parallel-distributed-training-of-speech-dnns/},
  keywords        = {quantization, gradient, parallel, speech}
}

@Article{sejdinovic2013-equivalence,
  author          = "Sejdinovic, Dino and Sriperumbudur, Bharath and Gretton, Arthur and Fukumizu, Kenji",
  title           = {Equivalence of Distance-Based and Rkhs-Based Statistics in Hypothesis Testing},
  journaltitle    = "Ann. Statist.",
  year            = 2013,
  volume          = 41,
  number          = 5,
  month           = 10,
  pages           = "2263--2291",
  doi             = "10.1214/13-AOS1140",
  url             = {https://doi.org/10.1214/13-AOS1140},
  journal         = "Ann. Statist.",
  fjournal        = "The Annals of Statistics",
  publisher       = "The Institute of Mathematical Statistics"
}

@Article{selvaraju2016-grad,
  author          = {Selvaraju, Ramprasaath R and Das, Abhishek and Vedantam, Ramakrishna and Cogswell, Michael and Parikh, Devi and Batra,
                  Dhruv},
  title           = {Grad-Cam: Why Did You Say That? Visual Explanations From Deep Networks Via Gradient-Based Localization},
  journaltitle    = {arXiv preprint arXiv:1610.02391},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1610.02391}
}

@Article{sengupta2017-securing,
  author          = {Sengupta, Sailik and Chakraborti, Tathagata and Kambhampati, Subbarao},
  title           = {Securing Deep Neural Nets Against Adversarial Attacks With Moving Target Defense},
  journaltitle    = {arXiv preprint arXiv:1705.07213},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.07213}
}

@Article{sennrich2015-improving,
  author          = {Sennrich, Rico and Haddow, Barry and Birch, Alexandra},
  title           = {Improving Neural Machine Translation Models With Monolingual Data},
  journaltitle    = {arXiv preprint arXiv:1511.06709},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1511.06709}
}

@Article{sennrich2015-neural,
  author          = {Sennrich, Rico and Haddow, Barry and Birch, Alexandra},
  title           = {Neural Machine Translation of Rare Words With Subword Units},
  journaltitle    = {arXiv preprint arXiv:1508.07909},
  year            = 2015,
  keywords        = {rare word, word piece model, wpm, neural machine translation, nmt},
  journal         = {arXiv preprint arXiv:1508.07909}
}

@Article{sennrich2017-nematus,
  author          = {Rico Sennrich and Orhan Firat and Kyunghyun Cho and Alexandra Birch and Barry Haddow and Julian Hitschler and Marcin
                  Junczys{-}Dowmunt and Samuel L{\"{a}}ubli and Antonio Valerio Miceli Barone and Jozef Mokry and Maria Nadejde},
  title           = {Nematus: a Toolkit for Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.04357},
  keywords        = {nmt},
  journal         = {CoRR}
}

@Article{seo2016-bidirectional,
  author          = {Min Joon Seo and Aniruddha Kembhavi and Ali Farhadi and Hannaneh Hajishirzi},
  title           = {Bidirectional Attention Flow for Machine Comprehension},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.01603},
  url             = {http://arxiv.org/abs/1611.01603},
  keywords        = {bidaf, qa},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SeoKFH16},
  timestamp       = {Wed, 07 Jun 2017 14:41:03 +0200}
}

@Article{serdyuk2017-twin,
  author          = {Serdyuk, Dmitriy and Ke, Rosemary Nan and Sordoni, Alessandro and Pal, Chris and Bengio, Yoshua},
  title           = {Twin Networks: Using the Future As a Regularizer},
  journaltitle    = {arXiv preprint arXiv:1708.06742},
  year            = 2017,
  keywords        = {regularization, rnn},
  journal         = {arXiv preprint arXiv:1708.06742}
}

@Article{sexton1999-beyond,
  author          = {Sexton, Randall S. and Dorsey, Robert E. and Johnson, John D.},
  title           = {Beyond Back Propagation: Using Simulated Annealing for Training Neural Networks},
  journaltitle    = {J. End User Comput.},
  year            = 1999,
  volume          = 11,
  number          = 3,
  month           = jul,
  pages           = {3--10},
  issn            = {1063-2239},
  url             = {http://dl.acm.org/citation.cfm?id=329748.329752},
  journal         = {J. End User Comput.},
  acmid           = 329752,
  address         = {Hershey, PA, USA},
  issue_date      = {July/Sept. 1999},
  numpages        = 8,
  publisher       = {IGI Global}
}

@Article{shalev-shwartz2010-learnability,
  author          = {Shalev-Shwartz, Shai and Shamir, Ohad and Srebro, Nathan and Sridharan, Karthik},
  title           = {Learnability, Stability and Uniform Convergence},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2010,
  volume          = 11,
  number          = {Oct},
  pages           = {2635--2670},
  journal         = {Journal of Machine Learning Research}
}

@Book{shalev-shwartz2014-understanding,
  author          = {Shalev-Shwartz, Shai and Ben-David, Shai},
  title           = {Understanding machine learning: From theory to algorithms},
  year            = 2014,
  publisher       = {Cambridge university press}
}

@Article{shameli2018-continuation,
  author          = {{Shameli}, A. and {Abbasi-Yadkori}, Y.},
  title           = {{A Continuation Method for Discrete Optimization and Its Application To Nearest Neighbor Classification}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.03482},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180203482S},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG"
}

@Article{shang2016-understanding,
  author          = {Wenling Shang and Kihyuk Sohn and Diogo Almeida and Honglak Lee},
  title           = {Understanding and Improving Convolutional Neural Networks Via Concatenated Rectified Linear Units},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.05201},
  url             = {http://arxiv.org/abs/1603.05201},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ShangSAL16},
  timestamp       = {Sat, 02 Apr 2016 11:49:48 +0200}
}

@InProceedings{sharir2018-expressive,
  author          = {Or Sharir and Amnon Shashua},
  title           = {On the Expressive Power of Overlapping Architectures of Deep Learning},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HkNGsseC-}
}

@InProceedings{shayer2018-learning,
  author          = {Oran Shayer and Dan Levi and Ethan Fetaya},
  title           = {Learning Discrete Weights Using the Local Reparameterization Trick},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=BySRH6CpW},
  keywords        = {quantization}
}

@Article{shazeer2017-outrageously,
  author          = {Noam Shazeer and Azalia Mirhoseini and Krzysztof Maziarz and Andy Davis and Quoc V. Le and Geoffrey E. Hinton and Jeff
                  Dean},
  title           = {Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1701.06538},
  journal         = {CoRR}
}

@Article{shen2015-minimum,
  author          = {Shiqi Shen and Yong Cheng and Zhongjun He and Wei He and Hua Wu and Maosong Sun and Yang Liu},
  title           = {Minimum Risk Training for Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.02433},
  url             = {http://arxiv.org/abs/1512.02433},
  keywords        = {nmt},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ShenCHHWSL15},
  timestamp       = {Sat, 02 Jan 2016 11:38:49 +0100}
}

@Article{shepard1971-mental,
  author          = {Shepard, Roger N. and Metzler, Jacqueline},
  title           = {Mental Rotation of Three-Dimensional Objects},
  keywords        = {mental rotation},
  journaltitle    = {Science},
  year            = 1971,
  volume          = 171,
  number          = 3972,
  pages           = {701--703},
  issn            = {0036-8075},
  doi             = {10.1126/science.171.3972.701},
  eprint          = {http://science.sciencemag.org/content/171/3972/701.full.pdf},
  url             = {https://doi.org/10.1126/science.171.3972.701},
  journal         = {Science},
  publisher       = {American Association for the Advancement of Science},
  timestamp       = {20181218T1442}
}

@InProceedings{sher2011-dxnn,
  author          = {Sher, Gene},
  title           = {DXNN: evolving complex organisms in complex environments using a novel tweann system},
  year            = 2011,
  booktitle       = {Proceedings of the 13th annual conference companion on Genetic and evolutionary computation},
  organization    = {ACM},
  pages           = {149--150}
}

@InProceedings{shi1998-modified,
  author          = {Shi, Yuhui and Eberhart, Russell},
  title           = {A Modified Particle Swarm Optimizer},
  year            = 1998,
  booktitle       = {Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE
                  International Conference on},
  organization    = {IEEE},
  pages           = {69--73}
}

@Article{shi2009-hash,
  author          = {Shi, Qinfeng and Petterson, James and Dror, Gideon and Langford, John and Smola, Alex and Vishwanathan, SVN},
  title           = {Hash Kernels for Structured Data},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2009,
  volume          = 10,
  number          = {Nov},
  pages           = {2615--2637},
  journal         = {Journal of Machine Learning Research}
}

@InCollection{shi2015-convolutional,
  author          = {SHI, Xingjian and Chen, Zhourong and Wang, Hao and Yeung, Dit-Yan and Wong, Wai-kin and WOO, Wang-chun},
  title           = {Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {802--810},
  url             =
                  {http://papers.nips.cc/paper/5955-convolutional-lstm-network-a-machine-learning-approach-for-precipitation-nowcasting.pdf}
}

@InProceedings{shi2017-jointly,
  author          = {Bei Shi and Wai Lam and Shoaib Jameel and Steven Schockaert and Kwun Ping Lai},
  title           = {Jointly Learning Word Embeddings and Latent Topics},
  year            = 2017,
  booktitle       = {SIGIR}
}

@Article{shillcock2000-eye,
  author          = {Shillcock, Richard and Ellison, T Mark and Monaghan, Padraic},
  title           = {Eye-Fixation Behavior, Lexical Storage, and Visual Word Recognition in a Split Processing Model.},
  keywords        = {brain, linguistic, psycho},
  journaltitle    = {Psychological review},
  year            = 2000,
  volume          = 107,
  number          = 4,
  pages           = 824,
  journal         = {Psychological review},
  publisher       = {American Psychological Association},
  timestamp       = {20190106T1050}
}

@Article{shimodaira2000-improving,
  author          = {Shimodaira, Hidetoshi},
  title           = {Improving Predictive Inference Under Covariate Shift By Weighting the Log-Likelihood Function},
  journaltitle    = {Journal of statistical planning and inference},
  year            = 2000,
  volume          = 90,
  number          = 2,
  pages           = {227--244},
  journal         = {Journal of statistical planning and inference},
  publisher       = {Elsevier}
}

@Article{shrikumar2017-learning,
  author          = {Avanti Shrikumar and Peyton Greenside and Anshul Kundaje},
  title           = {Learning Important Features Through Propagating Activation Differences},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.02685},
  eprint          = {1704.02685},
  url             = {http://arxiv.org/abs/1704.02685},
  keywords        = {interpret},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/ShrikumarGK17},
  timestamp       = {Wed, 07 Jun 2017 14:42:28 +0200}
}

@Article{shrivastava2016-learning,
  author          = {Ashish Shrivastava and Tomas Pfister and Oncel Tuzel and Josh Susskind and Wenda Wang and Russell Webb},
  title           = {Learning From Simulated and Unsupervised Images Through Adversarial Training},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.07828},
  journal         = {CoRR}
}

@Article{shwartz-ziv2017-opening,
  author          = {Ravid Shwartz{-}Ziv and Naftali Tishby},
  title           = {Opening the Black Box of Deep Neural Networks Via Information},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.00810},
  journal         = {CoRR}
}

@Article{shyam2017-attentive,
  author          = {Pranav Shyam and Shubham Gupta and Ambedkar Dukkipati},
  title           = {Attentive Recurrent Comparators},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.00767},
  keywords        = {meta learning},
  journal         = {CoRR}
}

@Article{silver2016-mastering,
  author          = {Silver, David and Huang, Aja and Maddison, Chris J.  and Guez, Arthur and Sifre, Laurent and van den Driessche, George
                  and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and Dieleman, Sander and
                  Grewe, Dominik and Nham, John and Kalchbrenner, Nal and Sutskever, Ilya and Lillicrap, Timothy and Leach, Madeleine and
                  Kavukcuoglu, Koray and Graepel, Thore and Hassabis, Demis},
  title           = {Mastering the Game of Go With Deep Neural Networks and Tree Search},
  journaltitle    = {Nature},
  year            = 2016,
  volume          = 529,
  number          = 7587,
  month           = {Jan},
  pages           = {484-489},
  note            = {Article},
  issn            = {0028-0836},
  url             = {http://dx.doi.org/10.1038/nature16961},
  journal         = {Nature},
  day             = 28,
  publisher       = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.}
}

@Article{silver2017-mastering,
  author          = {Silver, David and Schrittwieser, Julian and Simonyan, Karen and Antonoglou, Ioannis and Huang, Aja and Guez, Arthur and
                  Hubert, Thomas and Baker, Lucas and Lai, Matthew and Bolton, Adrian and Chen, Yutian and Lillicrap, Timothy and Hui, Fan
                  and Sifre, Laurent and van den Driessche, George and Graepel, Thore and Hassabis, Demis},
  title           = {Mastering the Game of Go Without Human Knowledge},
  journaltitle    = {Nature},
  year            = 2017,
  volume          = 550,
  number          = 7676,
  month           = {Oct},
  pages           = {354-359},
  note            = {Article},
  issn            = {0028-0836},
  url             = {http://dx.doi.org/10.1038/nature24270},
  journal         = {Nature},
  day             = 19,
  publisher       = {Macmillan Publishers Limited, part of Springer Nature. All rights reserved.}
}

@Article{silver2017-mastering-1,
  author          = {{Silver}, D. and {Hubert}, T. and {Schrittwieser}, J. and {Antonoglou}, I. and {Lai}, M. and {Guez}, A. and {Lanctot},
                  M. and {Sifre}, L. and {Kumaran}, D. and {Graepel}, T. and {Lillicrap}, T. and {Simonyan}, K. and {Hassabis}, D.},
  title           = {{Mastering Chess and Shogi By Self-Play With a General Reinforcement Learning Algorithm}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.01815},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171201815S},
  archiveprefix   = "arXiv",
  primaryclass    = "cs.AI"
}

@Article{simard1994-backpropagation,
  author          = {Simard, Patrice Y and Graf, Hans Peter},
  title           = {Backpropagation Without Multiplication},
  journaltitle    = {Advances in Neural Information Processing Systems},
  year            = 1994,
  pages           = {232--232},
  journal         = {Advances in Neural Information Processing Systems},
  publisher       = {MORGAN KAUFMANN PUBLISHERS}
}

@Article{simonyan2013-deep,
  author          = {Karen Simonyan and Andrea Vedaldi and Andrew Zisserman},
  title           = {Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1312.6034},
  url             = {http://arxiv.org/abs/1312.6034},
  keywords        = {interpret},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SimonyanVZ13},
  timestamp       = {Mon, 06 Jan 2014 15:10:41 +0100}
}

@Article{simonyan2014-very,
  author          = {Karen Simonyan and Andrew Zisserman},
  title           = {Very Deep Convolutional Networks for Large-Scale Image Recognition},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1409.1556},
  url             = {http://arxiv.org/abs/1409.1556},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SimonyanZ14a},
  timestamp       = {Wed, 01 Oct 2014 15:00:05 +0200}
}

@InCollection{sindhwani2015-structured,
  author          = {Sindhwani, Vikas and Sainath, Tara and Kumar, Sanjiv},
  title           = {Structured Transforms for Small-Footprint Deep Learning},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3088--3096},
  url             = {http://papers.nips.cc/paper/5869-structured-transforms-for-small-footprint-deep-learning.pdf}
}

@Article{singh2017-gated,
  author          = {{Singh Chaplot}, D. and {Mysore Sathyendra}, K. and {Pasumarthi}, R.~K. and {Rajagopal}, D. and {Salakhutdinov}, R.},
  title           = {{Gated-Attention Architectures for Task-Oriented Language Grounding}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.07230},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language,
                  Computer Science - Robotics},
  primaryclass    = "cs.LG"
}

@InProceedings{sinha2014-bilevel,
  author          = {Sinha, Ankur and Malo, Pekka and Xu, Peng and Deb, Kalyanmoy},
  title           = {A Bilevel Optimization Approach To Automated Parameter Tuning},
  year            = 2014,
  booktitle       = {Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation},
  organization    = {ACM},
  pages           = {847--854}
}

@Article{skurichina2002-bagging,
  author          = {Skurichina, Marina and Duin, Robert PW},
  title           = {Bagging, Boosting and the Random Subspace Method for Linear Classifiers},
  journaltitle    = {Pattern Analysis \& Applications},
  year            = 2002,
  volume          = 5,
  number          = 2,
  pages           = {121--135},
  journal         = {Pattern Analysis \& Applications},
  publisher       = {Springer}
}

@Article{smilkov2017-smoothgrad,
  author          = {Daniel Smilkov and Nikhil Thorat and Been Kim and Fernanda B. Vi{\'{e}}gas and Martin Wattenberg},
  title           = {Smoothgrad: Removing Noise By Adding Noise},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.03825},
  eprint          = {1706.03825},
  url             = {http://arxiv.org/abs/1706.03825},
  keywords        = {interpret},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/SmilkovTKVW17},
  timestamp       = {Mon, 03 Jul 2017 13:29:02 +0200}
}

@Article{smith2012-adversarial,
  author          = {Noah A. Smith},
  title           = {Adversarial Evaluation for Models of Natural Language},
  journaltitle    = {CoRR},
  year            = 2012,
  volume          = {abs/1207.0245},
  url             = {http://arxiv.org/abs/1207.0245},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1207-0245},
  timestamp       = {Wed, 10 Oct 2012 21:28:53 +0200}
}

@Article{smith2015-no,
  author          = {Leslie N. Smith},
  title           = {No More Pesky Learning Rate Guessing Games},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.01186},
  journal         = {CoRR}
}

@Article{smith2017-dont,
  author          = {Samuel L. Smith and Pieter{-}Jan Kindermans and Quoc V. Le},
  title           = {Don't Decay the Learning Rate, Increase the Batch Size},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.00489},
  journal         = {CoRR}
}

@Article{smith2017-offline,
  author          = {Smith, Samuel L and Turban, David HP and Hamblin, Steven and Hammerla, Nils Y},
  title           = {Offline Bilingual Word Vectors, Orthogonal Transformations and the Inverted Softmax},
  journaltitle    = {arXiv preprint arXiv:1702.03859},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1702.03859},
  timestamp       = {20190109T1059}
}

@Book{smolensky1986-parallel,
  author          = {Smolensky, P.},
  title           = {Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1},
  year            = 1986,
  editor          = {Rumelhart, David E. and McClelland, James L. and PDP Research Group, CORPORATE},
  publisher       = {MIT Press},
  isbn            = {0-262-68053-X},
  chapter         = {Information Processing in Dynamical Systems: Foundations of Harmony Theory},
  pages           = {194--281},
  url             = {http://dl.acm.org/citation.cfm?id=104279.104290},
  acmid           = 104290,
  address         = {Cambridge, MA, USA},
  numpages        = 88
}

@Article{snell2017-prototypical,
  author          = {Jake Snell and Kevin Swersky and Richard S. Zemel},
  title           = {Prototypical Networks for Few-Shot Learning},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.05175},
  keywords        = {meta learning, few shot},
  journal         = {CoRR}
}

@InProceedings{socher2013-recursive,
  author          = {Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D and Ng, Andrew and Potts,
                  Christopher},
  title           = {Recursive deep models for semantic compositionality over a sentiment treebank},
  year            = 2013,
  booktitle       = {Proceedings of the 2013 conference on empirical methods in natural language processing},
  pages           = {1631--1642},
  keywords        = {data, sst}
}

@Article{sohl-dickstein2013-adaptive,
  author          = {Jascha Sohl{-}Dickstein and Ben Poole and Surya Ganguli},
  title           = {An Adaptive Low Dimensional Quasi-Newton Sum of Functions Optimizer},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1311.2115},
  url             = {http://arxiv.org/abs/1311.2115},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Sohl-DicksteinPG13},
  timestamp       = {Tue, 03 Dec 2013 15:04:21 +0100}
}

@InCollection{sohn2015-learning,
  author          = {Sohn, Kihyuk and Lee, Honglak and Yan, Xinchen},
  title           = {Learning Structured Output Representation using Deep Conditional Generative Models},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {3483--3491},
  url             =
                  {http://papers.nips.cc/paper/5775-learning-structured-output-representation-using-deep-conditional-generative-models.pdf}
}

@Article{sompolinsky1988-statistical,
  author          = {Sompolinsky, Haim},
  title           = {Statistical Mechanics of Neural Networks},
  journaltitle    = {Physics Today},
  year            = 1988,
  volume          = 41,
  number          = 21,
  pages           = {70--80},
  journal         = {Physics Today}
}

@Article{sompolinsky1990-learning,
  author          = {Sompolinsky, Haim and Tishby, Naftali and Seung, H Sebastian},
  title           = {Learning From Examples in Large Neural Networks},
  journaltitle    = {Physical Review Letters},
  year            = 1990,
  volume          = 65,
  number          = 13,
  pages           = 1683,
  keywords        = {quantization},
  journal         = {Physical Review Letters},
  publisher       = {APS}
}

@Article{song2017-binary,
  author          = {Jingkuan Song},
  title           = {Binary Generative Adversarial Networks for Image Retrieval},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1708.04150},
  eprint          = {1708.04150},
  url             = {http://arxiv.org/abs/1708.04150},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1708-04150},
  timestamp       = {Mon, 13 Aug 2018 16:47:34 +0200}
}

@InCollection{song2017-complexity,
  author          = {Song, Le and Vempala, Santosh and Wilmes, John and Xie, Bo},
  title           = {On the Complexity of Learning Neural Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5520--5528},
  url             = {http://papers.nips.cc/paper/7135-on-the-complexity-of-learning-neural-networks.pdf}
}

@Article{song2017-multi,
  author          = {Song, Chang and Cheng, Hsin-Pai and Wu, Chunpeng and Li, Hai and Chen, Yiran and Wu, Qing},
  title           = {A Multi-Strength Adversarial Training Method To Mitigate Adversarial Attacks},
  journaltitle    = {arXiv preprint arXiv:1705.09764},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1705.09764}
}

@Article{song2017-pixeldefend,
  author          = {{Song}, Y. and {Kim}, T. and {Nowozin}, S. and {Ermon}, S. and {Kushman}, N.},
  title           = {{PixelDefend: Leveraging Generative Models To Understand and Defend Against Adversarial Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.10766},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171010766S},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "cs.LG"
}

@Article{song2018-defense,
  author          = {{Song}, S. and {Chen}, Y. and {Cheung}, N.-M. and {Kuo}, C.-C.~J.},
  title           = {{Defense Against Adversarial Attacks With Saak Transform}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.01785},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180801785S},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "cs.CV"
}

@Article{sordoni2016-iterative,
  author          = {{Sordoni}, A. and {Bachman}, P. and {Bengio}, Y.},
  title           = {{Iterative Alternating Neural Attention for Machine Reading}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.02245},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "cs.CL"
}

@InProceedings{soudry2014-expectation,
  author          = {Soudry, Daniel and Hubara, Itay and Meir, Ron},
  title           = {Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights},
  year            = 2014,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {963--971},
  keywords        = {quantization, training, expectation backpropagation}
}

@Article{soudry2017-implicit,
  author          = {Soudry, Daniel and Hoffer, Elad and Srebro, Nathan},
  title           = {The Implicit Bias of Gradient Descent on Separable Data},
  journaltitle    = {arXiv preprint arXiv:1710.10345},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1710.10345},
  timestamp       = {20181218T1412}
}

@InProceedings{sparks2015-automating,
  author          = {Sparks, Evan R and Talwalkar, Ameet and Haas, Daniel and Franklin, Michael J and Jordan, Michael I and Kraska, Tim},
  title           = {Automating model search for large scale machine learning},
  year            = 2015,
  booktitle       = {Proceedings of the Sixth ACM Symposium on Cloud Computing},
  organization    = {ACM},
  pages           = {368--380}
}

@InProceedings{sprechmann2018-memory,
  author          = {Pablo Sprechmann and Siddhant Jayakumar and Jack Rae and Alexander Pritzel and Adria Puigdomenech Badia and Benigno
                  Uria and Oriol Vinyals and Demis Hassabis and Razvan Pascanu and Charles Blundell},
  title           = {Memory-based Parameter Adaptation},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=rkfOvGbCW},
  keywords        = {mbpa}
}

@Article{spring2016-scalable,
  author          = {{Spring}, R. and {Shrivastava}, A.},
  title           = {{Scalable and Sustainable Deep Learning Via Randomized Hashing}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = feb,
  eprint          = {1602.08194},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {lsh, locality sensitive hashing, adaptive dropout, sparse update, computation cost},
  primaryclass    = "stat.ML"
}

@Article{springenberg2014-striving,
  author          = {Jost Tobias Springenberg and Alexey Dosovitskiy and Thomas Brox and Martin A. Riedmiller},
  title           = {Striving for Simplicity: The All Convolutional Net},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6806},
  journal         = {CoRR}
}

@Article{srivastava2014-dropout,
  author          = {Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
  title           = {Dropout: A Simple Way To Prevent Neural Networks From Overfitting},
  journaltitle    = {J. Mach. Learn. Res.},
  year            = 2014,
  volume          = 15,
  number          = 1,
  month           = jan,
  pages           = {1929--1958},
  issn            = {1532-4435},
  url             = {http://dl.acm.org/citation.cfm?id=2627435.2670313},
  journal         = {J. Mach. Learn. Res.},
  acmid           = 2670313,
  issue_date      = {January 2014},
  keywords        = {dropout, deep learning, model combination, neural networks, regularization},
  numpages        = 30,
  publisher       = {JMLR.org}
}

@Article{srivastava2015-highway,
  author          = {Rupesh Kumar Srivastava and Klaus Greff and J{\"u}rgen Schmidhuber},
  title           = {Highway Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1505.00387},
  url             = {http://arxiv.org/abs/1505.00387},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SrivastavaGS15},
  timestamp       = {Mon, 01 Jun 2015 14:13:54 +0200}
}

@InCollection{srivastava2015-training,
  author          = {Srivastava, Rupesh K and Greff, Klaus and Schmidhuber, Juergen},
  title           = {Training Very Deep Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2377--2385},
  url             = {http://papers.nips.cc/paper/5850-training-very-deep-networks.pdf},
  keywords        = {highway}
}

@Article{stachenfeld2017-hippocampus,
  author          = {Stachenfeld, Kimberly L.  and Botvinick, Matthew M.  and Gershman, Samuel J.},
  title           = {The Hippocampus As a Predictive Map},
  journaltitle    = {Nature Neuroscience},
  year            = 2017,
  volume          = 20,
  month           = {Oct},
  pages           = {1643 EP -},
  note            = {Article},
  url             = {http://dx.doi.org/10.1038/nn.4650},
  journal         = {Nature Neuroscience},
  day             = 02,
  publisher       = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved. SN -}
}

@Article{stallkamp2012-man,
  author          = "J. Stallkamp and M. Schlipsing and J. Salmen and C. Igel",
  title           = {Man Vs. Computer: Benchmarking Machine Learning Algorithms for Traffic Sign Recognition},
  journaltitle    = "Neural Networks",
  year            = 2012,
  volume          = 32,
  number          = "Supplement C",
  pages           = "323 - 332",
  note            = "Selected Papers from IJCNN 2011",
  issn            = "0893-6080",
  doi             = "https://doi.org/10.1016/j.neunet.2012.02.016",
  url             = {https://doi.org/https://doi.org/10.1016/j.neunet.2012.02.016},
  journal         = "Neural Networks",
  keywords        = {traffic sign}
}

@InProceedings{stanley2002-efficient,
  author          = {Kenneth O. Stanley and Risto Miikkulainen},
  title           = {Efficient Reinforcement Learning Through Evolving Neural Network Topologies},
  year            = 2002,
  booktitle       = {Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002)},
  publisher       = {Morgan Kaufmann},
  pages           = 9,
  url             = "http://nn.cs.utexas.edu/?stanley:gecco02b",
  address         = {San Francisco}
}

@Article{stanley2002-evolving,
  author          = {Stanley, Kenneth O and Miikkulainen, Risto},
  title           = {Evolving Neural Networks Through Augmenting Topologies},
  journaltitle    = {Evolutionary computation},
  year            = 2002,
  volume          = 10,
  number          = 2,
  pages           = {99--127},
  journal         = {Evolutionary computation},
  keywords        = {evolution, genetic, neuro evolution of augmenting topologies, neat, survey},
  publisher       = {MIT Press}
}

@Article{stanley2005-real,
  author          = {K. O. Stanley and B. D. Bryant and R. Miikkulainen},
  title           = {Real-Time Neuroevolution in the Nero Video Game},
  journaltitle    = {IEEE Transactions on Evolutionary Computation},
  year            = 2005,
  volume          = 9,
  number          = 6,
  month           = Dec,
  pages           = {653-668},
  issn            = {1089-778X},
  doi             = {10.1109/TEVC.2005.856210},
  journal         = {IEEE Transactions on Evolutionary Computation},
  keywords        = {augmented reality;computer games;evolutionary computation;learning (artificial intelligence);neural nets;real-time
                  systems;robots;NERO video game;artificial neural network;augmenting topologies;machine learning;neuroevolving robotic
                  operatives game;real-time neuroevolution;virtual robots;Artificial intelligence;Artificial neural networks;Computer
                  science education;Games;Industrial training;Machine learning;Network topology;Neural networks;Robots;Toy
                  industry;Interactive;neural networks;neuroevolution;neuroevolution of augmenting topologies (NEAT);neuroevolving robotic
                  operatives (NERO);online;real-time;video games}
}

@Article{stanley2007-compositional,
  author          = {Stanley, Kenneth O},
  title           = {Compositional Pattern Producing Networks: A Novel Abstraction of Development},
  journaltitle    = {Genetic programming and evolvable machines},
  year            = 2007,
  volume          = 8,
  number          = 2,
  pages           = {131--162},
  journal         = {Genetic programming and evolvable machines},
  publisher       = {Springer}
}

@Article{stanley2009-hypercube,
  author          = {Stanley, Kenneth O and D'Ambrosio, David B and Gauci, Jason},
  title           = {A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks},
  journaltitle    = {Artificial life},
  year            = 2009,
  volume          = 15,
  number          = 2,
  pages           = {185--212},
  journal         = {Artificial life},
  publisher       = {MIT Press}
}

@InProceedings{steil2004-backpropagation,
  author          = {Steil, Jochen J},
  title           = {Backpropagation-decorrelation: online recurrent learning with O (N) complexity},
  year            = 2004,
  booktitle       = {Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on},
  volume          = 2,
  organization    = {IEEE},
  pages           = {843--848},
  keywords        = {backpropagation decorrelation, bpdc}
}

@Article{storn1997-differential,
  author          = {Storn, Rainer and Price, Kenneth},
  title           = {Differential Evolution--a Simple and Efficient Heuristic for Global Optimization Over Continuous Spaces},
  journaltitle    = {Journal of global optimization},
  year            = 1997,
  volume          = 11,
  number          = 4,
  pages           = {341--359},
  keywords        = {optimization, genetic},
  journal         = {Journal of global optimization},
  publisher       = {Springer}
}

@Article{strobelt2016-visual,
  author          = {Hendrik Strobelt and Sebastian Gehrmann and Bernd Huber and Hanspeter Pfister and Alexander M. Rush},
  title           = {Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.07461},
  eprint          = {1606.07461},
  url             = {http://arxiv.org/abs/1606.07461},
  keywords        = {interpret},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/StrobeltGHPR16},
  timestamp       = {Wed, 07 Jun 2017 14:41:49 +0200}
}

@Article{strobl2007-bias,
  author          = "Strobl, Carolin and Boulesteix, Anne-Laure and Zeileis, Achim and Hothorn, Torsten",
  title           = {Bias in Random Forest Variable Importance Measures: Illustrations, Sources and a Solution},
  journaltitle    = "BMC Bioinformatics",
  year            = 2007,
  volume          = 8,
  number          = 1,
  month           = "Jan",
  pages           = 25,
  issn            = "1471-2105",
  doi             = "10.1186/1471-2105-8-25",
  url             = {https://doi.org/10.1186/1471-2105-8-25},
  journal         = "BMC Bioinformatics",
  day             = 25
}

@InProceedings{su2014-nesterovs,
  author          = {Su, Weijie and Boyd, Stephen and Candes, Emmanuel},
  title           = {A differential equation for modeling Nesterov's accelerated gradient method: Theory and insights},
  year            = 2014,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {2510--2518}
}

@Article{su2017-one,
  author          = {{Su}, J. and {Vasconcellos Vargas}, D. and {Kouichi}, S.},
  title           = {{One Pixel Attack for Fooling Deep Neural networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.08864},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171008864S},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack, evolution},
  primaryclass    = "cs.LG"
}

@InCollection{su2017-probabilistic,
  author          = {Su, Qinliang and Liao, xuejun and Carin, Lawrence},
  title           = {A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4489--4498},
  url             = {http://papers.nips.cc/paper/7035-a-probabilistic-framework-for-nonlinearities-in-stochastic-neural-networks.pdf}
}

@Article{subramanian2018-learning,
  author          = {Sandeep Subramanian and Adam Trischler and Yoshua Bengio and Christopher J. Pal},
  title           = {Learning General Purpose Distributed Sentence Representations Via Large Scale Multi-Task Learning},
  keywords        = {embedding, sentence},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1804.00079},
  eprint          = {1804.00079},
  url             = {http://arxiv.org/abs/1804.00079},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1804-00079},
  timestamp       = {20190103T1618}
}

@InProceedings{sugiyama2008-direct,
  author          = {Sugiyama, Masashi and Nakajima, Shinichi and Kashima, Hisashi and Buenau, Paul V and Kawanabe, Motoaki},
  title           = {Direct importance estimation with model selection and its application to covariate shift adaptation},
  year            = 2008,
  booktitle       = {Advances in neural information processing systems},
  pages           = {1433--1440}
}

@InCollection{sukhbaatar2015-end,
  author          = {Sukhbaatar, Sainbayar and szlam, arthur and Weston, Jason and Fergus, Rob},
  title           = {End-To-End Memory Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2440--2448},
  url             = {http://papers.nips.cc/paper/5846-end-to-end-memory-networks.pdf}
}

@InProceedings{sun2013-deep,
  author          = {Sun, Yi and Wang, Xiaogang and Tang, Xiaoou},
  title           = {Deep convolutional network cascade for facial point detection},
  year            = 2013,
  booktitle       = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages           = {3476--3483},
  keywords        = {dynamic}
}

@Article{sun2015-pronet,
  author          = {Chen Sun and Manohar Paluri and Ronan Collobert and Ram Nevatia and Lubomir D. Bourdev},
  title           = {Pronet: Learning To Propose Object-Specific Boxes for Cascaded Neural Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.03776},
  keywords        = {dynamic},
  journal         = {CoRR}
}

@InCollection{sun2015-space,
  author          = {Sun, Ke and Wang, Jun and Kalousis, Alexandros and Marchand-Maillet, Stephane},
  title           = {Space-Time Local Embeddings},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {100--108},
  url             = {http://papers.nips.cc/paper/5971-space-time-local-embeddings.pdf}
}

@Article{sun2017-simple,
  author          = {Yifan Sun and Nikhil Rao and Weicong Ding},
  title           = {A Simple Approach To Learn Polysemous Word Embeddings},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.01793},
  eprint          = {1707.01793},
  url             = {http://arxiv.org/abs/1707.01793},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/SunRD17},
  timestamp       = {Sat, 05 Aug 2017 14:56:00 +0200}
}

@Article{sundararajan2017-axiomatic,
  author          = {Sundararajan, Mukund and Taly, Ankur and Yan, Qiqi},
  title           = {Axiomatic Attribution for Deep Networks},
  journaltitle    = {arXiv preprint arXiv:1703.01365},
  year            = 2017,
  keywords        = {interpret},
  journal         = {arXiv preprint arXiv:1703.01365}
}

@InProceedings{susskind2011-modeling,
  author          = {Susskind, Joshua and Hinton, Geoffrey and Memisevic, Roland and Pollefeys, Marc},
  title           = {Modeling the joint density of two images under a variety of transformations},
  keywords        = {disentangle},
  year            = 2011,
  booktitle       = {Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on},
  organization    = {IEEE},
  pages           = {2793--2800},
  timestamp       = {20190110T0940}
}

@InProceedings{sutskever2010-convergence,
  author          = {Ilya Sutskever and Tijmen Tieleman},
  title           = {On the convergence properties of contrastive divergence},
  year            = 2010,
  booktitle       = {In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS}
}

@Article{sutskever2014-sequence,
  author          = {Ilya Sutskever and Oriol Vinyals and Quoc V. Le},
  title           = {Sequence To Sequence Learning With Neural Networks},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1409.3215},
  url             = {http://arxiv.org/abs/1409.3215},
  keywords        = {rnn, translation},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SutskeverVL14},
  timestamp       = {Wed, 01 Oct 2014 15:00:04 +0200}
}

@Article{sutton1999-between,
  author          = "Richard S. Sutton and Doina Precup and Satinder Singh",
  title           = {Between Mdps and Semi-Mdps: A Framework for Temporal Abstraction in Reinforcement Learning},
  journaltitle    = "Artificial Intelligence",
  year            = 1999,
  volume          = 112,
  number          = 1,
  pages           = "181 - 211",
  issn            = "0004-3702",
  doi             = "https://doi.org/10.1016/S0004-3702(99)00052-1",
  url             = {https://doi.org/https://doi.org/10.1016/S0004-3702(99)00052-1},
  journal         = "Artificial Intelligence",
  keywords        = "Temporal abstraction, Reinforcement learning, Markov decision processes, Options, Macros, Macroactions, Subgoals,
                  Intra-option learning, Hierarchical planning, Semi-Markov decision processes"
}

@Book{sutton2014-reinforcement,
  author          = {Sutton, Richard S and Barto, Andrew G},
  title           = {Reinforcement learning: An introduction},
  year            = 2014,
  volume          = 1,
  edition         = 2,
  number          = 1,
  publisher       = {MIT press Cambridge}
}

@InCollection{suwajanakorn2018-discovery,
  author          = {Suwajanakorn, Supasorn and Snavely, Noah and Tompson, Jonathan J and Norouzi, Mohammad},
  title           = {Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2063--2074},
  url             = {http://papers.nips.cc/paper/7476-discovery-of-latent-3d-keypoints-via-end-to-end-geometric-reasoning.pdf},
  timestamp       = {20181207T1055}
}

@Article{swirszcz2016-local,
  author          = {{Swirszcz}, G. and {Czarnecki}, W.~M. and {Pascanu}, R.},
  title           = {{Local Minima in Training of Neural networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = nov,
  eprint          = {1611.06310},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2016arXiv161106310S},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML"
}

@Article{szegedy2013-intriguing,
  author          = {Christian Szegedy and Wojciech Zaremba and Ilya Sutskever and Joan Bruna and Dumitru Erhan and Ian J. Goodfellow and
                  Rob Fergus},
  title           = {Intriguing Properties of Neural Networks},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1312.6199},
  url             = {http://arxiv.org/abs/1312.6199},
  keywords        = {adversarial, attack, lbfgs, transfer},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SzegedyZSBEGF13},
  timestamp       = {Mon, 06 Jan 2014 15:10:41 +0100}
}

@Article{szegedy2014-going,
  author          = {Christian Szegedy and Wei Liu and Yangqing Jia and Pierre Sermanet and Scott Reed and Dragomir Anguelov and Dumitru
                  Erhan and Vincent Vanhoucke and Andrew Rabinovich},
  title           = {Going Deeper With Convolutions},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1409.4842},
  url             = {http://arxiv.org/abs/1409.4842},
  keywords        = {pruning},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/SzegedyLJSRAEVR14},
  timestamp       = {Wed, 01 Oct 2014 15:00:05 +0200}
}

@InProceedings{szegedy2016-rethinking,
  author          = {Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jon and Wojna, Zbigniew},
  title           = {Rethinking the Inception Architecture for Computer Vision},
  year            = 2016,
  booktitle       = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages           = {2818--2826},
  keywords        = {inception v3}
}

@InProceedings{szegedy2017-inception,
  author          = {Szegedy, Christian and Ioffe, Sergey and Vanhoucke, Vincent and Alemi, Alexander A},
  title           = {Inception-v4, inception-resnet and the impact of residual connections on learning.},
  year            = 2017,
  booktitle       = {AAAI},
  volume          = 4,
  pages           = 12,
  keywords        = {inception v4}
}

@Article{szepesvari2009-algorithms,
  author          = {Szepesv{\'a}ri, Csaba},
  title           = {Algorithms for Reinforcement Learning},
  journaltitle    = {Morgan and Claypool},
  year            = 2009,
  journal         = {Morgan and Claypool},
  publisher       = {Citeseer}
}

@Article{szepesvari2010-algorithms,
  author          = {Szepesv{\'a}ri, Csaba},
  title           = {Algorithms for Reinforcement Learning},
  journaltitle    = {Synthesis lectures on artificial intelligence and machine learning},
  year            = 2010,
  volume          = 4,
  number          = 1,
  pages           = {1--103},
  journal         = {Synthesis lectures on artificial intelligence and machine learning},
  publisher       = {Morgan \& Claypool Publishers}
}

@InProceedings{szumlanski2013-new,
  author          = {Szumlanski, Sean and Gomez, Fernando and Sims, Valerie K},
  title           = {A New Set of Norms for Semantic Relatedness Measures},
  year            = 2013,
  booktitle       = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  volume          = 2,
  pages           = {890--895},
  keywords        = {rel-122}
}

@Article{tabacof2015-exploring,
  author          = {Tabacof, Pedro and Valle, Eduardo},
  title           = {Exploring the Space of Adversarial Images},
  journaltitle    = {arXiv preprint arXiv:1510.05328},
  year            = 2015,
  keywords        = {adversarial},
  journal         = {arXiv preprint arXiv:1510.05328}
}

@Article{tabacof2016-adversarial,
  author          = {Pedro Tabacof and Julia Tavares and Eduardo Valle},
  title           = {Adversarial Images for Variational Autoencoders},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.00155},
  url             = {http://arxiv.org/abs/1612.00155},
  keywords        = {adversarial, attack, vae, generative},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/TabacofTV16},
  timestamp       = {Wed, 07 Jun 2017 14:40:22 +0200}
}

@Article{tachet2018-learning,
  author          = {{Tachet des Combes}, R. and {Pezeshki}, M. and {Shabanian}, S. and {Courville}, A. and {Bengio}, Y.},
  title           = {{On the Learning Dynamics of Deep Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = sep,
  eprint          = {1809.06848},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180906848T},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning}
}

@Article{tai2015-convolutional,
  author          = {Cheng Tai and Tong Xiao and Xiaogang Wang and Weinan E},
  title           = {Convolutional Neural Networks With Low-Rank Regularization},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06067},
  keywords        = {pruning, low rank},
  journal         = {CoRR}
}

@Article{tai2015-improved,
  author          = {Tai, Kai Sheng and Socher, Richard and Manning, Christopher D},
  title           = {Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks},
  keywords        = {tree lstm},
  journaltitle    = {arXiv preprint arXiv:1503.00075},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1503.00075}
}

@InCollection{takens1981-detecting,
  author          = {Takens, Floris},
  title           = {Detecting strange attractors in turbulence},
  year            = 1981,
  booktitle       = {Dynamical systems and turbulence, Warwick 1980},
  publisher       = {Springer},
  pages           = {366--381}
}

@InProceedings{tallec2018-can,
  author          = {Corentin Tallec and Yann Ollivier},
  title           = {Can Recurrent Neural Networks Warp Time?},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SJcKhk-Ab}
}

@Article{tamar2016-value,
  author          = {Aviv Tamar and Sergey Levine and Pieter Abbeel},
  title           = {Value Iteration Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1602.02867},
  url             = {http://arxiv.org/abs/1602.02867},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/TamarLA16},
  timestamp       = {Tue, 01 Mar 2016 17:47:25 +0100}
}

@Article{tan2018-lattice,
  author          = "Zhixing Tan and Jinsong Su and Boli Wang and Yidong Chen and Xiaodong Shi",
  title           = {Lattice-To-Sequence Attentional Neural Machine Translation Models},
  journaltitle    = "Neurocomputing",
  year            = 2018,
  volume          = 284,
  pages           = "138 - 147",
  issn            = "0925-2312",
  doi             = "https://doi.org/10.1016/j.neucom.2018.01.010",
  url             = {https://doi.org/https://doi.org/10.1016/j.neucom.2018.01.010},
  journal         = "Neurocomputing",
  keywords        = "Neural Machine Translation, Word lattice, Recurrent Neural Network, Gated Recurrent Unit"
}

@Article{tanay2016-boundary,
  author          = {Thomas Tanay and Lewis D. Griffin},
  title           = {A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1608.07690},
  keywords        = {adversarial, hypothesizes},
  journal         = {CoRR}
}

@Article{tang2013-deep,
  author          = {Yichuan Tang},
  title           = {Deep Learning Using Support Vector Machines},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1306.0239},
  url             = {http://arxiv.org/abs/1306.0239},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Tang13},
  timestamp       = {Mon, 01 Jul 2013 20:31:24 +0200}
}

@InCollection{teh2001-rate,
  author          = {Teh, Yee Whye and Geoffrey E. Hinton},
  title           = {Rate-coded Restricted Boltzmann Machines for Face Recognition},
  year            = 2001,
  booktitle       = {Advances in Neural Information Processing Systems 13},
  editor          = {T.K. Leen and T.G. Dietterich and V. Tresp},
  publisher       = {MIT Press},
  pages           = {908--914},
  url             = {http://papers.nips.cc/paper/1886-rate-coded-restricted-boltzmann-machines-for-face-recognition.pdf}
}

@Article{tekin2017-real,
  author          = {Bugra Tekin and Sudipta N. Sinha and Pascal Fua},
  title           = {Real-Time Seamless Single Shot 6d Object Pose Prediction},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.08848},
  eprint          = {1711.08848},
  url             = {http://arxiv.org/abs/1711.08848},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1711-08848},
  timestamp       = {20181206T0920}
}

@InCollection{theis2015-generative,
  author          = {Theis, Lucas and Bethge, Matthias},
  title           = {Generative Image Modeling Using Spatial LSTMs},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {1927--1935},
  url             = {http://papers.nips.cc/paper/5637-generative-image-modeling-using-spatial-lstms.pdf}
}

@Article{thomas2017-disentangling,
  author          = {Thomas, Valentin and Bengio, Emmanuel and Fedus, William and Pondard, Jules and Beaudoin, Philippe and Larochelle, Hugo
                  and Pineau, Joelle and Precup, Doina and Bengio, Yoshua},
  title           = {Disentangling the Independently Controllable Factors of Variation By Interacting With the World},
  keywords        = {disentangle},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1708.01289},
  journal         = {CoRR}
}

@Book{thompson2016-visual,
  author          = {Thompson, William and Fleming, Roland and Creem-Regehr, Sarah and Stefanucci, Jeanine Kelly},
  title           = {Visual Perception from A Computer Graphics Perspective},
  year            = 2016,
  publisher       = {AK Peters/CRC Press},
  timestamp       = {20190104T1617}
}

@InProceedings{tian2014-probabilistic,
  author          = {Tian, Fei and Dai, Hanjun and Bian, Jiang and Gao, Bin and Zhang, Rui and Chen, Enhong and Liu, Tie-Yan},
  title           = {A Probabilistic Model for Learning Multi-Prototype Word Embeddings},
  year            = 2014,
  booktitle       = {Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers},
  pages           = {151--160}
}

@Article{tian2015-better,
  author          = {Yuandong Tian and Yan Zhu},
  title           = {Better Computer Go Player With Neural Network and Long-Term Prediction},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06410},
  url             = {http://arxiv.org/abs/1511.06410},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/TianZ15},
  timestamp       = {Tue, 01 Dec 2015 19:22:34 +0100}
}

@InProceedings{tieleman2008-training,
  author          = {Tieleman, Tijmen},
  title           = {Training Restricted Boltzmann Machines Using Approximations to the Likelihood Gradient},
  year            = 2008,
  booktitle       = {Proceedings of the 25th International Conference on Machine Learning},
  series          = {ICML '08},
  publisher       = {ACM},
  location        = {Helsinki, Finland},
  isbn            = {978-1-60558-205-4},
  pages           = {1064--1071},
  doi             = {10.1145/1390156.1390290},
  url             = {http://doi.acm.org/10.1145/1390156.1390290},
  acmid           = 1390290,
  address         = {New York, NY, USA},
  numpages        = 8
}

@Article{tishby2015-deep,
  author          = {Naftali Tishby and Noga Zaslavsky},
  title           = {Deep Learning and the Information Bottleneck Principle},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1503.02406},
  journal         = {CoRR}
}

@Article{toderici2015-variable,
  author          = {George Toderici and Sean M. O'Malley and Sung Jin Hwang and Damien Vincent and David Minnen and Shumeet Baluja and
                  Michele Covell and Rahul Sukthankar},
  title           = {Variable Rate Image Compression With Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06085},
  url             = {http://arxiv.org/abs/1511.06085},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/TodericiOHVMBCS15},
  timestamp       = {Wed, 07 Jun 2017 14:42:31 +0200}
}

@Article{toderici2016-full,
  author          = {{Toderici}, G. and {Vincent}, D. and {Johnston}, N. and {Hwang}, S.~J. and {Minnen}, D. and {Shor}, J. and {Covell},
                  M.},
  title           = {{Full Resolution Image Compression With Recurrent Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = aug,
  eprint          = {1608.05148},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition},
  primaryclass    = "cs.CV"
}

@Misc{todoTODO-todo,
  author          = {TODO},
  title           = {TODO},
  year            = {TODO},
  note            = {TODO},
  journal         = {TODO},
  publisher       = {TODO},
  volume          = {TODO}
}

@InProceedings{todorov2012-mujoco,
  author          = {Todorov, Emanuel and Erez, Tom and Tassa, Yuval},
  title           = {Mujoco: A physics engine for model-based control},
  year            = 2012,
  booktitle       = {Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on},
  organization    = {IEEE},
  pages           = {5026--5033}
}

@Article{toffoli2000-what,
  author          = {{Toffoli}, T.},
  title           = {{What You Always Wanted To Know About Genetic Algorithms But Were Afraid To hear}},
  journaltitle    = {eprint arXiv:nlin/0007013},
  year            = 2000,
  month           = jul,
  eprint          = {nlin/0007013},
  journal         = {eprint arXiv:nlin/0007013},
  keywords        = {Nonlinear Sciences - Adaptation and Self-Organizing Systems}
}

@Article{toneva2018-empirical,
  author          = {Toneva, Mariya and Sordoni, Alessandro and Combes, Remi Tachet des and Trischler, Adam and Bengio, Yoshua and Gordon,
                  Geoffrey J},
  title           = {An Empirical Study of Example Forgetting During Deep Neural Network Learning},
  keywords        = {forget},
  journaltitle    = {arXiv preprint arXiv:1812.05159},
  year            = 2018,
  journal         = {arXiv preprint arXiv:1812.05159},
  timestamp       = {20181218T0827}
}

@InProceedings{topchy1996-fast,
  author          = {Topchy, Alexander P and Lebedko, Oleg A and Miagkikh, Victor V},
  title           = {Fast learning in multilayered neural networks by means of hybrid evolutionary and gradient algorithms},
  year            = 1996,
  booktitle       = {Proc. of IC on Evolutionary Computation and Its Applications, Moscow},
  organization    = {Citeseer}
}

@Article{torralba2003-statistics,
  author          = {Torralba, Antonio and Oliva, Aude},
  title           = {Statistics of Natural Image Categories},
  journaltitle    = {Network: computation in neural systems},
  year            = 2003,
  volume          = 14,
  number          = 3,
  pages           = {391--412},
  journal         = {Network: computation in neural systems},
  publisher       = {Taylor \& Francis}
}

@Article{touchette2011-basic,
  author          = {{Touchette}, H.},
  title           = {{A Basic Introduction To Large Deviations: Theory, Applications, simulations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2011,
  month           = jun,
  eprint          = {1106.4146},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Condensed Matter - Statistical Mechanics, Mathematical Physics},
  primaryclass    = "cond-mat.stat-mech"
}

@Article{trabelsi2017-deep,
  author          = {{Trabelsi}, C. and {Bilaniuk}, O. and {Serdyuk}, D. and {Subramanian}, S. and {Santos}, J.~F. and {Mehri}, S. and
                  {Rostamzadeh}, N. and {Bengio}, Y. and {Pal}, C.~J},
  title           = {{Deep Complex Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.09792},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Neural and Evolutionary Computing, Computer Science - Learning}
}

@InProceedings{tramer2016-stealing,
  author          = {Tram{\`e}r, Florian and Zhang, Fan and Juels, Ari and Reiter, Michael K and Ristenpart, Thomas},
  title           = {Stealing Machine Learning Models via Prediction APIs.},
  year            = 2016,
  booktitle       = {USENIX Security Symposium},
  pages           = {601--618}
}

@Article{tramer2017-ensemble,
  author          = {Tram{\`e}r, Florian and Kurakin, Alexey and Papernot, Nicolas and Boneh, Dan and McDaniel, Patrick},
  title           = {Ensemble Adversarial Training: Attacks and Defenses},
  journaltitle    = {arXiv preprint arXiv:1705.07204},
  year            = 2017,
  keywords        = {adversarial, defense},
  journal         = {arXiv preprint arXiv:1705.07204}
}

@Article{tramer2017-space,
  author          = {Tram{\`e}r, Florian and Papernot, Nicolas and Goodfellow, Ian and Boneh, Dan and McDaniel, Patrick},
  title           = {The Space of Transferable Adversarial Examples},
  journaltitle    = {arXiv preprint arXiv:1704.03453},
  year            = 2017,
  keywords        = {adversarial, hypothesis, gaas},
  journal         = {arXiv preprint arXiv:1704.03453}
}

@InCollection{tran2017-bayesian,
  author          = {Tran, Toan and Pham, Trung and Carneiro, Gustavo and Palmer, Lyle and Reid, Ian},
  title           = {A Bayesian Data Augmentation Approach for Learning Deep Models},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2794--2803},
  url             = {http://papers.nips.cc/paper/6872-a-bayesian-data-augmentation-approach-for-learning-deep-models.pdf}
}

@Book{treil2017-linear,
  author          = {Sergei Treil},
  title           = {Linear Algebra Done Wrong},
  year            = 2017,
  eprint          = {Brown University},
  url             = {https://www.math.brown.edu/~treil/papers/LADW/LADW.html}
}

@InCollection{triantafillou2017-few,
  author          = {Triantafillou, Eleni and Zemel, Richard and Urtasun, Raquel},
  title           = {Few-Shot Learning Through an Information Retrieval Lens},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2252--2262},
  url             = {http://papers.nips.cc/paper/6820-few-shot-learning-through-an-information-retrieval-lens.pdf}
}

@InProceedings{tsang2018-detecting,
  author          = {Michael Tsang and Dehua Cheng and Yan Liu},
  title           = {Detecting Statistical Interactions from Neural Network Weights},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=ByOfBggRZ},
  keywords        = {interpret, nid}
}

@Article{tsitsiklis1997-analysis,
  author          = {J. N. Tsitsiklis and B. Van Roy},
  title           = {An Analysis of Temporal-Difference Learning With Function Approximation},
  journaltitle    = {IEEE Transactions on Automatic Control},
  year            = 1997,
  volume          = 42,
  number          = 5,
  month           = {May},
  pages           = {674-690},
  issn            = {0018-9286},
  doi             = {10.1109/9.580874},
  url             = {https://doi.org/10.1109/9.580874},
  journal         = {IEEE Transactions on Automatic Control},
  timestamp       = {20181201T1004}
}

@InProceedings{turcanik2016-hash,
  author          = {M. Tur{\v{c}}an{\'i}k and M. Javurek},
  title           = {Hash function generation by neural network},
  year            = 2016,
  booktitle       = {2016 New Trends in Signal Processing (NTSP)},
  month           = {Oct},
  pages           = {1-5},
  doi             = {10.1109/NTSP.2016.7747793},
  url             = {https://doi.org/10.1109/NTSP.2016.7747793},
  keywords        = {index}
}

@Article{ullrich2017-soft,
  author          = {{Ullrich}, K. and {Meeds}, E. and {Welling}, M.},
  title           = {{Soft Weight-Sharing for Neural Network Compression}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.04008},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {quantization, regularizer, soft weight sharing},
  primaryclass    = "stat.ML"
}

@Article{upadhyay2016-cross,
  author          = {Shyam Upadhyay and Manaal Faruqui and Chris Dyer and Dan Roth},
  title           = {Cross-Lingual Models of Word Embeddings: An Empirical Comparison},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1604.00425},
  journal         = {CoRR}
}

@Article{urbanczik2009-reinforcement,
  author          = {Urbanczik, Robert and Senn, Walter},
  title           = {Reinforcement Learning in Populations of Spiking Neurons},
  journaltitle    = {Nature neuroscience},
  year            = 2009,
  volume          = 12,
  number          = 3,
  pages           = 250,
  journal         = {Nature neuroscience},
  publisher       = {Nature Publishing Group}
}

@Article{usunier2016-episodic,
  author          = {{Usunier}, N. and {Synnaeve}, G. and {Lin}, Z. and {Chintala}, S.},
  title           = {{Episodic Exploration for Deep Deterministic Policies: An Application To Starcraft Micromanagement Tasks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = sep,
  eprint          = {1609.02993},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Learning, I.2.1, I.2.6},
  primaryclass    = "cs.AI"
}

@InCollection{vahdat2017-toward,
  author          = {Vahdat, Arash},
  title           = {Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5601--5610},
  url             =
                  {http://papers.nips.cc/paper/7143-toward-robustness-against-label-noise-in-training-deep-discriminative-neural-networks.pdf}
}

@Article{valpola2014-from,
  author          = {{Valpola}, H.},
  title           = {{From Neural Pca To Deep Unsupervised learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2014,
  month           = nov,
  eprint          = {1411.7783},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML"
}

@InProceedings{van2012-stochastic,
  author          = {Van Der Maaten, Laurens and Weinberger, Kilian},
  title           = {Stochastic triplet embedding},
  year            = 2012,
  booktitle       = {2012 IEEE International Workshop on Machine Learning for Signal Processing},
  organization    = {IEEE},
  pages           = {1--6}
}

@Article{van2012-visualizing,
  author          = {Van der Maaten, Laurens and Hinton, Geoffrey},
  title           = {Visualizing Non-Metric Similarities in Multiple Maps},
  journaltitle    = {Machine learning},
  year            = 2012,
  volume          = 87,
  number          = 1,
  pages           = {33--55},
  journal         = {Machine learning},
  publisher       = {Springer}
}

@Article{vaswani2017-attention,
  author          = {{Vaswani}, A. and {Shazeer}, N. and {Parmar}, N. and {Uszkoreit}, J. and {Jones}, L. and {Gomez}, A.~N. and {Kaiser},
                  L. and {Polosukhin}, I.},
  title           = {{Attention Is All You Need}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.03762},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {transformer, seq2seq},
  primaryclass    = "cs.CL"
}

@Article{veit2016-disentangling,
  author          = {{Veit}, A. and {Belongie}, S. and {Karaletsos}, T.},
  title           = {{Disentangling Nonlinear Perceptual Embeddings With Multi-Query Triplet Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = mar,
  eprint          = {1603.07810},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {disentangle},
  primaryclass    = "cs.CV"
}

@InProceedings{veit2016-residual,
  author          = {Veit, Andreas and Wilber, Michael and Belongie, Serge},
  title           = {Residual Networks Behave Like Ensembles of Relatively Shallow Networks},
  year            = 2016,
  booktitle       = {Proceedings of the 30th International Conference on Neural Information Processing Systems},
  series          = {NIPS'16},
  publisher       = {Curran Associates Inc.},
  location        = {Barcelona, Spain},
  isbn            = {978-1-5108-3881-9},
  pages           = {550--558},
  url             = {http://dl.acm.org/citation.cfm?id=3157096.3157158},
  acmid           = 3157158,
  address         = {USA},
  numpages        = 9
}

@Article{velez2016-identifying,
  author          = {Velez, Roby and Clune, Jeff},
  title           = {Identifying Core Functional Networks and Functional Modules Within Artificial Neural Networks Via Subsets Regression},
  journaltitle    = {GECCO},
  year            = 2016,
  journal         = {GECCO}
}

@Article{velez2017-diffusion,
  author          = {Velez, Roby and Clune, Jeff},
  title           = {Diffusion-Based Neuromodulation Can Eliminate Catastrophic Forgetting in Simple Neural Networks},
  journaltitle    = {PloS one},
  year            = 2017,
  volume          = 12,
  number          = 11,
  pages           = {e0187736},
  journal         = {PloS one},
  publisher       = {Public Library of Science},
  timestamp       = {20181201T1002}
}

@Article{venkatesh2016-accelerating,
  author          = {Ganesh Venkatesh and Eriko Nurvitadhi and Debbie Marr},
  title           = {Accelerating Deep Convolutional Networks Using Low-Precision and Sparsity},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1610.00324},
  keywords        = {quantization},
  journal         = {CoRR}
}

@Article{verstraeten2007-experimental,
  author          = {Verstraeten, David and Schrauwen, Benjamin and d'Haene, Michiel and Stroobandt, Dirk},
  title           = {An Experimental Unification of Reservoir Computing Methods},
  journaltitle    = {Neural networks},
  year            = 2007,
  volume          = 20,
  number          = 3,
  pages           = {391--403},
  keywords        = {reservoir, survey},
  journal         = {Neural networks},
  publisher       = {Elsevier}
}

@Article{vilnis2014-word,
  author          = {Vilnis, Luke and McCallum, Andrew},
  title           = {Word Representations Via Gaussian Embedding},
  journaltitle    = {arXiv preprint arXiv:1412.6623},
  year            = 2014,
  journal         = {arXiv preprint arXiv:1412.6623}
}

@Article{vincent2010-stacked,
  author          = {Vincent, Pascal and Larochelle, Hugo and Lajoie, Isabelle and Bengio, Yoshua and Manzagol, Pierre-Antoine},
  title           = {Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network With a Local Denoising Criterion},
  journaltitle    = {J. Mach. Learn. Res.},
  year            = 2010,
  volume          = 11,
  month           = dec,
  pages           = {3371--3408},
  issn            = {1532-4435},
  url             = {http://dl.acm.org/citation.cfm?id=1756006.1953039},
  journal         = {J. Mach. Learn. Res.},
  acmid           = 1953039,
  issue_date      = {3/1/2010},
  numpages        = 38,
  publisher       = {JMLR.org}
}

@Article{vinyals2014-grammar,
  author          = {Oriol Vinyals and Lukasz Kaiser and Terry Koo and Slav Petrov and Ilya Sutskever and Geoffrey E. Hinton},
  title           = {Grammar As a Foreign Language},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.7449},
  url             = {http://arxiv.org/abs/1412.7449},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/VinyalsKKPSH14},
  timestamp       = {Thu, 01 Jan 2015 19:51:08 +0100}
}

@Article{vinyals2014-show,
  author          = {Oriol Vinyals and Alexander Toshev and Samy Bengio and Dumitru Erhan},
  title           = {Show and Tell: {A} Neural Image Caption Generator},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1411.4555},
  url             = {http://arxiv.org/abs/1411.4555},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/VinyalsTBE14},
  timestamp       = {Mon, 01 Dec 2014 14:32:13 +0100}
}

@InCollection{vinyals2015-pointer,
  author          = {Vinyals, Oriol and Fortunato, Meire and Jaitly, Navdeep},
  title           = {Pointer Networks},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2692--2700},
  url             = {http://papers.nips.cc/paper/5866-pointer-networks.pdf},
  keywords        = {pointer, convex hull, tsp, delaunay}
}

@Article{vinyals2016-matching,
  author          = {{Vinyals}, O. and {Blundell}, C. and {Lillicrap}, T. and {Kavukcuoglu}, K. and {Wierstra}, D.},
  title           = {{Matching Networks for One Shot Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = jun,
  eprint          = {1606.04080},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {meta learning, one shot},
  primaryclass    = "cs.LG"
}

@InCollection{volkovs2017-dropoutnet,
  author          = {Volkovs, Maksims and Yu, Guangwei and Poutanen, Tomi},
  title           = {DropoutNet: Addressing Cold Start in Recommender Systems},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {4964--4973},
  url             = {http://papers.nips.cc/paper/7081-dropoutnet-addressing-cold-start-in-recommender-systems.pdf}
}

@InCollection{volokitin2017-do,
  author          = {Volokitin, Anna and Roig, Gemma and Poggio, Tomaso A},
  title           = {Do Deep Neural Networks Suffer from Crowding?},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5633--5643},
  url             = {http://papers.nips.cc/paper/7146-do-deep-neural-networks-suffer-from-crowding.pdf}
}

@Misc{vreeken2003-spiking,
  author          = {Vreeken, Jilles},
  title           = {Spiking neural networks, an introduction},
  year            = 2003,
  publisher       = {Utrecht University: Information and Computing Sciences}
}

@InProceedings{vu2016-k,
  author          = {Thuy Vu and Douglas Stott Parker},
  title           = {\$K\$-Embeddings: Learning Conceptual Embeddings for Words using Context},
  year            = 2016,
  booktitle       = {HLT-NAACL}
}

@Article{waestlund2009-replica,
  author          = {{W{\"a}stlund}, J.},
  title           = {{Replica Symmetry and Combinatorial Optimization}},
  journaltitle    = {ArXiv e-prints},
  year            = 2009,
  month           = aug,
  eprint          = {0908.1920},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Mathematics - Probability, 60C05, 82B44, 90C35, 91A43},
  primaryclass    = "math.PR"
}

@InProceedings{wan2013-regularization,
  author          = {Wan, Li and Zeiler, Matthew and Zhang, Sixin and Cun, Yann L and Fergus, Rob},
  title           = {Regularization of neural networks using dropconnect},
  year            = 2013,
  booktitle       = {Proceedings of the 30th International Conference on Machine Learning (ICML-13)},
  pages           = {1058--1066}
}

@Article{wang2014-attentional,
  author          = {Qian Wang and Jiaxing Zhang and Sen Song and Zheng Zhang},
  title           = {Attentional Neural Network: Feature Selection Using Cognitive Feedback},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1411.5140},
  url             = {http://arxiv.org/abs/1411.5140},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WangZSZ14},
  keywords        = {feature selection, neural network,},
  timestamp       = {Tue, 02 Dec 2014 08:04:26 +0100}
}

@Article{wang2014-gaussian,
  author          = {Nan Wang and Jan Melchior and Laurenz Wiskott},
  title           = {Gaussian-Binary Restricted Boltzmann Machines on Modeling Natural Image Statistics},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1401.5900},
  url             = {http://arxiv.org/abs/1401.5900},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WangMW14},
  timestamp       = {Sun, 02 Feb 2014 18:37:28 +0100}
}

@Article{wang2014-hashing,
  author          = {Jingdong Wang and Heng Tao Shen and Jingkuan Song and Jianqiu Ji},
  title           = {Hashing for Similarity Search: {A} Survey},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1408.2927},
  keywords        = {survey, index},
  journal         = {CoRR}
}

@InProceedings{wang2015-deep,
  author          = {Wang, Weiran and Arora, Raman and Livescu, Karen and Bilmes, Jeff},
  title           = {On Deep Multi-View Representation Learning},
  year            = 2015,
  booktitle       = {Proc. of the 32st Int. Conf. Machine Learning (ICML 2015)},
  pages           = {1083--1092}
}

@Article{wang2015-dueling,
  author          = {Ziyu Wang and Nando de Freitas and Marc Lanctot},
  title           = {Dueling Network Architectures for Deep Reinforcement Learning},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.06581},
  journal         = {CoRR}
}

@Article{wang2015-learning,
  author          = {Wang, Shuohang and Jiang, Jing},
  title           = {Learning Natural Language Inference With Lstm},
  journaltitle    = {arXiv preprint arXiv:1512.08849},
  year            = 2015,
  keywords        = {match-lstm, text inference},
  journal         = {arXiv preprint arXiv:1512.08849}
}

@Article{wang2015-statistical,
  author          = {{Wang}, C. and {Chen}, M.-H. and {Schifano}, E. and {Wu}, J. and {Yan}, J.},
  title           = {{Statistical Methods and Computing for Big Data}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = feb,
  eprint          = {1502.07989},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2015arXiv150207989W},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Computation, Mathematics - Statistics Theory},
  primaryclass    = "stat.CO"
}

@InProceedings{wang2016-cse,
  author          = {Yashen Wang and Heyan Huang and Chong Feng and Qiang Zhou and Jiahui Gu and Xiong Gao},
  title           = {CSE: Conceptual Sentence Embeddings based on Attention Model},
  year            = 2016,
  booktitle       = {ACL}
}

@Article{wang2016-generative,
  author          = {Xiaolong Wang and Abhinav Gupta},
  title           = {Generative Image Modeling Using Style and Structure Adversarial Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1603.05631},
  url             = {http://arxiv.org/abs/1603.05631},
  journal         = {CoRR},
  timestamp       = {Fri, 18 Aug 2017 15:54:43 +0200}
}

@Article{wang2016-machine,
  author          = {Shuohang Wang and Jing Jiang},
  title           = {Machine Comprehension Using Match-Lstm and Answer Pointer},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1608.07905},
  url             = {http://arxiv.org/abs/1608.07905},
  keywords        = {match-lstm, pointer, qa},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WangJ16a},
  timestamp       = {Wed, 07 Jun 2017 14:40:40 +0200}
}

@Article{wang2016-noisy,
  author          = {Wang, Yu-Xiang and Xu, Huan},
  title           = {Noisy Sparse Subspace Clustering},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2016,
  volume          = 17,
  number          = 12,
  pages           = {1--41},
  keywords        = {cluster},
  journal         = {Journal of Machine Learning Research}
}

@Article{wang2016-random,
  author          = {Wang, Yi and Li, Yi and Pu, Weilin and Wen, Kathryn and Shugart, Yin Yao and Xiong, Momiao and Jin, Li},
  title           = {Random Bits Forest: a Strong Classifier/regressor for Big Data},
  journaltitle    = {Scientific Reports},
  year            = 2016,
  volume          = 6,
  month           = {Jul},
  pages           = 30086,
  note            = {Article},
  url             = {http://dx.doi.org/10.1038/srep30086},
  journal         = {Scientific Reports},
  day             = 22
}

@InProceedings{wang2016-structural,
  author          = {Wang, Daixin and Cui, Peng and Zhu, Wenwu},
  title           = {Structural Deep Network Embedding},
  year            = 2016,
  booktitle       = {Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  series          = {KDD '16},
  publisher       = {ACM},
  location        = {San Francisco, California, USA},
  isbn            = {978-1-4503-4232-2},
  pages           = {1225--1234},
  doi             = {10.1145/2939672.2939753},
  url             = {https://doi.org/10.1145/2939672.2939753},
  acmid           = 2939753,
  address         = {New York, NY, USA},
  keywords        = {deep learning, network analysis, network embedding},
  numpages        = 10
}

@Article{wang2016-theoretical,
  author          = {Wang, Beilun and Gao, Ji and Qi, Yanjun},
  title           = {A Theoretical Framework for Robustness of (deep) Classifiers Under Adversarial Noise},
  journaltitle    = {arXiv preprint arXiv:1612.00334},
  year            = 2016,
  journal         = {arXiv preprint arXiv:1612.00334}
}

@Article{wang2016-towards,
  author          = {{Wang}, H. and {Yeung}, D.-Y.},
  title           = {{Towards Bayesian Deep Learning: A Survey}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = apr,
  eprint          = {1604.01662},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2016arXiv160401662W},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and
                  Pattern Recognition, Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "stat.ML"
}

@Article{wang2017-analyzing,
  author          = {{Wang}, Y. and {Jha}, S. and {Chaudhuri}, K.},
  title           = {{Analyzing the Robustness of Nearest Neighbors To Adversarial Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jun,
  eprint          = {1706.03922},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, hypothesis},
  primaryclass    = "stat.ML"
}

@Article{wang2017-attention,
  author          = {{Wang}, T. and {Cho}, K.},
  title           = {{Attention-Based Mixture Density Recurrent Networks for History-Based Recommendation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = sep,
  eprint          = {1709.07545},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Information Retrieval},
  primaryclass    = "cs.LG"
}

@InProceedings{wang2017-beyond,
  author          = {Wang, Yunhe and Xu, Chang and Xu, Chao and Tao, Dacheng},
  title           = {Beyond Filters: Compact Feature Map for Portable Deep Model},
  year            = 2017,
  booktitle       = {International Conference on Machine Learning},
  pages           = {3703--3711}
}

@Article{wang2017-detecting,
  author          = {Jianyu Wang and Cihang Xie and Zhishuai Zhang and Jun Zhu and Lingxi Xie and Alan L. Yuille},
  title           = {Detecting Semantic Parts on Partially Occluded Objects},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.07819},
  eprint          = {1707.07819},
  url             = {http://arxiv.org/abs/1707.07819},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/WangXZZXY17},
  timestamp       = {20181230T0943}
}

@InCollection{wang2017-differentially,
  author          = {Wang, Di and Ye, Minwei and Xu, Jinhui},
  title           = {Differentially Private Empirical Risk Minimization Revisited: Faster and More General},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2719--2728},
  url             =
                  {http://papers.nips.cc/paper/6865-differentially-private-empirical-risk-minimization-revisited-faster-and-more-general.pdf}
}

@InProceedings{wang2017-gated,
  author          = {Wang, Wenhui and Yang, Nan and Wei, Furu and Chang, Baobao and Zhou, Ming},
  title           = {Gated self-matching networks for reading comprehension and question answering},
  year            = 2017,
  booktitle       = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  volume          = 1,
  pages           = {189--198},
  keywords        = {rnet, qa}
}

@InProceedings{wang2017-hybrid,
  author          = {Wang, Chenglong and Jiang, Feijun and Yang, Hongxia},
  title           = {A Hybrid Framework for Text Modeling with Convolutional RNN},
  year            = 2017,
  booktitle       = {Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  series          = {KDD '17},
  publisher       = {ACM},
  location        = {Halifax, NS, Canada},
  isbn            = {978-1-4503-4887-4},
  pages           = {2061--2069},
  doi             = {10.1145/3097983.3098140},
  url             = {https://doi.org/10.1145/3097983.3098140},
  acmid           = 3098140,
  address         = {New York, NY, USA},
  keywords        = {answer selection, convolution neural network, hybrid framework, recurrent neural network, sentence classification, text
                  modeling},
  numpages        = 9
}

@Article{wang2017-k,
  author          = {Zhiguo Wang and Wael Hamza and Linfeng Song},
  title           = {K-Nearest Neighbor Augmented Neural Networks for Text Classification},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1708.07863},
  journal         = {CoRR}
}

@Article{wang2017-nearest,
  author          = {{Wang}, Z. and {Hamza}, W. and {Song}, L.},
  title           = {{$k$-Nearest Neighbor Augmented Neural Networks for Text Classification}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = aug,
  eprint          = {1708.07863},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {text classification, knn, attention, external memory},
  primaryclass    = "cs.CL"
}

@Article{wang2017-robust,
  author          = {Ziyu Wang and Josh Merel and Scott E. Reed and Greg Wayne and Nando de Freitas and Nicolas Heess},
  title           = {Robust Imitation of Diverse Behaviors},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.02747},
  journal         = {CoRR}
}

@Article{wang2017-sequence,
  author          = {{Wang}, C. and {Wang}, Y. and {Huang}, P.-S. and {Mohamed}, A. and {Zhou}, D. and {Deng}, L.},
  title           = {{Sequence Modeling Via Segmentations}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = feb,
  eprint          = {1702.07463},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML"
}

@Article{wang2017-tacotron,
  author          = {{Wang}, Y. and {Skerry-Ryan}, R. and {Stanton}, D. and {Wu}, Y. and {Weiss}, R.~J. and {Jaitly}, N. and {Yang}, Z. and
                  {Xiao}, Y. and {Chen}, Z. and {Bengio}, S. and {Le}, Q. and {Agiomyrgiannakis}, Y. and {Clark}, R. and {Saurous}, R.~A.},
  title           = {{Tacotron: A Fully End-To-End Text-To-Speech Synthesis Model}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.10135},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language, Computer Science - Learning, Computer Science - Sound},
  primaryclass    = "cs.CL"
}

@Article{wang2017-text,
  author          = {Heng Wang and Zengchang Qin and Tao Wan},
  title           = {Text Generation Based on Generative Adversarial Nets With Latent Variable},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1712.00170},
  eprint          = {1712.00170},
  url             = {http://arxiv.org/abs/1712.00170},
  keywords        = {gan, vae, text generation},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1712-00170},
  timestamp       = {Wed, 03 Jan 2018 12:33:17 +0100}
}

@InProceedings{wang2017-training,
  author          = {Shengjie Wang and Haoran Cai and Jeff Bilmes and William Noble},
  title           = {Training Compressed Fully-Connected Networks With A Density-Diversity Penalty},
  year            = 2017,
  booktitle       = {International Conference on Learning Representations (ICLR)},
  url             = {https://openreview.net/forum?id=Hku9NK5lx&noteId=Hku9NK5lx},
  keywords        = {compression, regularizer}
}

@Article{wang2017-visual,
  author          = {Jianyu Wang and Zhishuai Zhang and Cihang Xie and Yuyin Zhou and Vittal Premachandran and Jun Zhu and Lingxi Xie and
                  Alan L. Yuille},
  title           = {Visual Concepts and Compositional Voting},
  keywords        = {compositional, voting},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.04451},
  eprint          = {1711.04451},
  url             = {http://arxiv.org/abs/1711.04451},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1711-04451},
  timestamp       = {20181230T0942}
}

@Article{wang2018-detecting,
  author          = {{Wang}, J. and {Sun}, J. and {Zhang}, P. and {Wang}, X.},
  title           = {{Detecting Adversarial Samples for Deep Neural Networks Through Mutation Testing}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = may,
  eprint          = {1805.05010},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180505010W},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "cs.LG"
}

@InBook{warde-farley2016-adversarial,
  title           = {Adversarial Perturbations of Deep Neural Networks},
  year            = 2016,
  author          = {Warde-Farley, D and Goodfellow, I},
  booktitle       = {Perturbation, Optimization and Statistics},
  editor          = {Hazan, Tamir and Papandreou, George and Tarlow, Daniel},
  keywords        = {adversarial}
}

@Article{watkins1992-q,
  author          = {Watkins, Christopher JCH and Dayan, Peter},
  title           = {Q-Learning},
  journaltitle    = {Machine learning},
  year            = 1992,
  volume          = 8,
  number          = {3-4},
  pages           = {279--292},
  keywords        = {q learning},
  journal         = {Machine learning},
  publisher       = {Springer}
}

@Article{weber2018-controlling,
  author          = {{Weber}, N. and {Shekhar}, L. and {Balasubramanian}, N. and {Cho}, K.},
  title           = {{Controlling Decoding for More Abstractive Summaries With Copy-Based Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = mar,
  eprint          = {1803.07038},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180307038W},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL"
}

@InProceedings{wei2018-improving,
  author          = {Xiang Wei and Zixia Liu and Liqiang Wang and Boqing Gong},
  title           = {Improving the Improved Training of Wasserstein {GAN}s},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SJx9GQb0-}
}

@InCollection{weigend1991-generalization,
  author          = {Andreas S. Weigend and David E. Rumelhart and Bernardo A. Huberman},
  title           = {Generalization by Weight-Elimination with Application to Forecasting},
  year            = 1991,
  booktitle       = {Advances in Neural Information Processing Systems 3},
  editor          = {R. P. Lippmann and J. E. Moody and D. S. Touretzky},
  publisher       = {Morgan-Kaufmann},
  pages           = {875--882},
  url             = {http://papers.nips.cc/paper/323-generalization-by-weight-elimination-with-application-to-forecasting.pdf},
  keywords        = {pruning}
}

@InProceedings{wen2016-learning,
  author          = {Wen, Wei and Wu, Chunpeng and Wang, Yandan and Chen, Yiran and Li, Hai},
  title           = {Learning structured sparsity in deep neural networks},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {2074--2082},
  keywords        = {pruning, structured sparsity, compression, group lasso}
}

@Article{wen2017-coordinating,
  author          = {Wei Wen and Cong Xu and Chunpeng Wu and Yandan Wang and Yiran Chen and Hai Li},
  title           = {Coordinating Filters for Faster Deep Neural Networks},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.09746},
  keywords        = {compression},
  journal         = {CoRR}
}

@InProceedings{weng2014-recurrent,
  author          = {Weng, Chao and Yu, Dong and Watanabe, Shinji and Juang, Biing-Hwang Fred},
  title           = {Recurrent deep neural networks for robust speech recognition},
  year            = 2014,
  booktitle       = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  organization    = {IEEE},
  pages           = {5532--5536}
}

@Article{werbos1990-backpropagation,
  author          = {Werbos, Paul J},
  title           = {Backpropagation Through Time: What It Does and How To Do It},
  journaltitle    = {Proceedings of the IEEE},
  year            = 1990,
  volume          = 78,
  number          = 10,
  pages           = {1550--1560},
  keywords        = {backpropagation through time, bptt},
  journal         = {Proceedings of the IEEE},
  publisher       = {IEEE}
}

@InProceedings{weston2008-deep,
  author          = {Weston, Jason and Ratle, Fr{\'e}d{\'e}ric and Collobert, Ronan},
  title           = {Deep Learning via Semi-supervised Embedding},
  year            = 2008,
  booktitle       = {Proceedings of the 25th International Conference on Machine Learning},
  series          = {ICML '08},
  publisher       = {ACM},
  location        = {Helsinki, Finland},
  isbn            = {978-1-60558-205-4},
  pages           = {1168--1175},
  doi             = {10.1145/1390156.1390303},
  url             = {http://doi.acm.org/10.1145/1390156.1390303},
  acmid           = 1390303,
  address         = {New York, NY, USA},
  numpages        = 8
}

@Article{weston2014-memory,
  author          = {Jason Weston and Sumit Chopra and Antoine Bordes},
  title           = {Memory Networks},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1410.3916},
  url             = {http://arxiv.org/abs/1410.3916},
  keywords        = {differentiable programming},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WestonCB14},
  timestamp       = {Sun, 02 Nov 2014 11:25:59 +0100}
}

@Article{weston2015-towards,
  author          = {Jason Weston and Antoine Bordes and Sumit Chopra and Tomas Mikolov},
  title           = {Towards Ai-Complete Question Answering: {A} Set of Prerequisite Toy Tasks},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1502.05698},
  eprint          = {1502.05698},
  url             = {http://arxiv.org/abs/1502.05698},
  keywords        = {babl},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/WestonBCM15},
  timestamp       = {Mon, 13 Aug 2018 16:47:58 +0200}
}

@InProceedings{whitley1989-genitor,
  author          = {Whitley, L. Darrell},
  title           = {The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best},
  year            = 1989,
  booktitle       = {Proceedings of the 3rd International Conference on Genetic Algorithms},
  publisher       = {Morgan Kaufmann Publishers Inc.},
  isbn            = {1-55860-066-3},
  pages           = {116--123},
  url             = {http://dl.acm.org/citation.cfm?id=645512.657257},
  acmid           = 657257,
  address         = {San Francisco, CA, USA},
  numpages        = 8
}

@Article{whitley1990-genetic,
  author          = {Whitley, Darrell and Starkweather, Timothy and Bogart, Christopher},
  title           = {Genetic Algorithms and Neural Networks: Optimizing Connections and Connectivity},
  journaltitle    = {Parallel computing},
  year            = 1990,
  volume          = 14,
  number          = 3,
  pages           = {347--361},
  journal         = {Parallel computing},
  publisher       = {Elsevier}
}

@InCollection{whitley1993-genetic,
  author          = {Whitley, Darrell and Dominic, Stephen and Das, Rajarshi and Anderson, Charles W},
  title           = {Genetic reinforcement learning for neurocontrol problems},
  year            = 1993,
  booktitle       = {Genetic Algorithms for Machine Learning},
  publisher       = {Springer},
  pages           = {103--128}
}

@Article{whitley1995-genetic,
  author          = {Whitley, Darrell},
  title           = {Genetic Algorithms and Neural Networks},
  journaltitle    = {Genetic algorithms in engineering and computer science},
  year            = 1995,
  volume          = 3,
  pages           = {203--216},
  journal         = {Genetic algorithms in engineering and computer science},
  publisher       = {Citeseer}
}

@Article{whitley2001-overview,
  author          = {Whitley, Darrell},
  title           = {An Overview of Evolutionary Algorithms: Practical Issues and Common Pitfalls},
  journaltitle    = {Information and software technology},
  year            = 2001,
  volume          = 43,
  number          = 14,
  pages           = {817--831},
  journal         = {Information and software technology},
  publisher       = {Elsevier}
}

@Article{wibisono2016-variational,
  author          = {{Wibisono}, A. and {Wilson}, A.~C. and {Jordan}, M.~I.},
  title           = {{A Variational Perspective on Accelerated Methods in Optimization}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = mar,
  eprint          = {1603.04245},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Mathematics - Optimization and Control, Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "math.OC"
}

@Article{widrow2013-no,
  author          = {Widrow, Bernard and Greenblatt, Aaron and Kim, Youngsik and Park, Dookun},
  title           = {The No-Prop Algorithm: A New Learning Algorithm for Multilayer Neural Networks},
  journaltitle    = {Neural Networks},
  year            = 2013,
  volume          = 37,
  pages           = {182--188},
  journal         = {Neural Networks},
  publisher       = {Elsevier}
}

@Article{wierstra2014-natural,
  author          = {Wierstra, Daan and Schaul, Tom and Glasmachers, Tobias and Sun, Yi and Peters, Jan and Schmidhuber, J\"{u}rgen},
  title           = {Natural Evolution Strategies},
  journaltitle    = {J. Mach. Learn. Res.},
  year            = 2014,
  volume          = 15,
  number          = 1,
  month           = jan,
  pages           = {949--980},
  issn            = {1532-4435},
  url             = {http://dl.acm.org/citation.cfm?id=2627435.2638566},
  journal         = {J. Mach. Learn. Res.},
  acmid           = 2638566,
  issue_date      = {January 2014},
  keywords        = {nes},
  numpages        = 32,
  publisher       = {JMLR.org}
}

@Article{wieting2015-towards,
  author          = {John Wieting and Mohit Bansal and Kevin Gimpel and Karen Livescu},
  title           = {Towards Universal Paraphrastic Sentence Embeddings},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.08198},
  eprint          = {1511.08198},
  url             = {http://arxiv.org/abs/1511.08198},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/WietingBGL15a},
  timestamp       = {Wed, 07 Jun 2017 14:40:28 +0200}
}

@Article{wieting2017-learning,
  author          = {John Wieting and Jonathan Mallinson and Kevin Gimpel},
  title           = {Learning Paraphrastic Sentence Embeddings From Back-Translated Bitext},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.01847},
  eprint          = {1706.01847},
  url             = {http://arxiv.org/abs/1706.01847},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/WietingMG17},
  timestamp       = {Mon, 03 Jul 2017 13:29:02 +0200}
}

@Article{wieting2017-pushing,
  author          = {John Wieting and Kevin Gimpel},
  title           = {Pushing the Limits of Paraphrastic Sentence Embeddings With Millions of Machine Translations},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.05732},
  eprint          = {1711.05732},
  url             = {http://arxiv.org/abs/1711.05732},
  keywords        = {paranmt-50m},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1711-05732},
  timestamp       = {Sun, 03 Dec 2017 12:38:15 +0100}
}

@InCollection{williams1992-simple,
  author          = {Williams, Ronald J},
  title           = {Simple Statistical Gradient-following Algorithms for Connectionist Reinforcement Learning},
  year            = 1992,
  booktitle       = {Reinforcement Learning},
  publisher       = {Springer},
  pages           = {5--32},
  keywords        = {REINFORCE}
}

@Article{williams2018-optical,
  author          = {Williams, Robert Max and Yampolskiy, Roman V},
  title           = {Optical Illusions Images Dataset},
  journaltitle    = {arXiv preprint arXiv:1810.00415},
  year            = 2018,
  keywords        = {data},
  journal         = {arXiv preprint arXiv:1810.00415}
}

@InProceedings{wilson2016-stochastic,
  author          = {Wilson, Andrew G and Hu, Zhiting and Salakhutdinov, Ruslan R and Xing, Eric P},
  title           = {Stochastic Variational Deep Kernel Learning},
  year            = 2016,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {2586--2594}
}

@Article{wojna2017-devil,
  author          = {{Wojna}, Z. and {Ferrari}, V. and {Guadarrama}, S. and {Silberman}, N. and {Chen}, L.-C. and {Fathi}, A. and
                  {Uijlings}, J.},
  title           = {{The Devil Is in the Decoder}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.05847},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computer Vision and Pattern Recognition},
  primaryclass    = "cs.CV"
}

@Article{wolf2017-unsupervised,
  author          = {Wolf, Lior and Taigman, Yaniv and Polyak, Adam},
  title           = {Unsupervised Creation of Parameterized Avatars},
  journaltitle    = {arXiv preprint arXiv:1704.05693},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1704.05693}
}

@Article{wong2017-dancin,
  author          = {{Wong}, C.},
  title           = {{DANCin Seq2seq: Fooling Text Classifiers With Adversarial Text Example Generation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.05419},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171205419W},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, text, reinforcement},
  primaryclass    = "cs.LG"
}

@InProceedings{wong2018-provable,
  author          = {Wong, Eric and Kolter, Zico},
  title           = {Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope},
  keywords        = {adversarial, defense},
  year            = 2018,
  booktitle       = {International Conference on Machine Learning},
  pages           = {5283--5292},
  timestamp       = {20181230T1040}
}

@InCollection{wong2018-scaling,
  author          = {Wong, Eric and Schmidt, Frank and Metzen, Jan Hendrik and Kolter, J. Zico},
  title           = {Scaling Provable Adversarial Defenses},
  keywords        = {adversarial, defense},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {8410--8419},
  url             = {http://papers.nips.cc/paper/8060-scaling-provable-adversarial-defenses.pdf},
  timestamp       = {20181230T1041}
}

@InCollection{wu2015-galileo,
  author          = {Wu, Jiajun and Yildirim, Ilker and Lim, Joseph J and Freeman, Bill and Tenenbaum, Josh},
  title           = {Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {127--135},
  url             =
                  {http://papers.nips.cc/paper/5780-galileo-perceiving-physical-object-properties-by-integrating-a-physics-engine-with-deep-learning.pdf}
}

@Article{wu2015-quantized,
  author          = {Jiaxiang Wu and Cong Leng and Yuhang Wang and Qinghao Hu and Jian Cheng},
  title           = {Quantized Convolutional Neural Networks for Mobile Devices},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.06473},
  url             = {http://arxiv.org/abs/1512.06473},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WuLWHC15},
  timestamp       = {Sat, 02 Jan 2016 11:38:49 +0100}
}

@Article{wu2016-googles,
  author          = {{Wu}, Y. and {Schuster}, M. and {Chen}, Z. and {Le}, Q.~V. and {Norouzi}, M. and {Macherey}, W. and {Krikun}, M. and
                  {Cao}, Y. and {Gao}, Q. and {Macherey}, K. and {Klingner}, J. and {Shah}, A. and {Johnson}, M. and {Liu}, X. and {Kaiser},
                  {\L}. and {Gouws}, S. and {Kato}, Y. and {Kudo}, T. and {Kazawa}, H. and {Stevens}, K. and {Kurian}, G. and {Patil},
                  N. and {Wang}, W. and {Young}, C. and {Smith}, J. and {Riesa}, J. and {Rudnick}, A. and {Vinyals}, O. and {Corrado},
                  G. and {Hughes}, M. and {Dean}, J.},
  title           = {{Google's Neural Machine Translation System: Bridging the Gap Between Human and Machine Translation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = sep,
  eprint          = {1609.08144},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {nlp, nmt, neural machine translation, natural language processing, google},
  primaryclass    = "cs.CL"
}

@Article{wu2016-multiplicative,
  author          = {Yuhuai Wu and Saizheng Zhang and Ying Zhang and Yoshua Bengio and Ruslan Salakhutdinov},
  title           = {On Multiplicative Integration With Recurrent Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.06630},
  url             = {http://arxiv.org/abs/1606.06630},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WuZZBS16},
  timestamp       = {Fri, 01 Jul 2016 17:39:49 +0200}
}

@Article{wu2016-quantitative,
  author          = {Yuhuai Wu and Yuri Burda and Ruslan Salakhutdinov and Roger B. Grosse},
  title           = {On the Quantitative Analysis of Decoder-Based Generative Models},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.04273},
  url             = {http://arxiv.org/abs/1611.04273},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WuBSG16},
  timestamp       = {Thu, 01 Dec 2016 19:32:08 +0100}
}

@Article{wu2017-adversarial,
  author          = {Lijun Wu and Yingce Xia and Li Zhao and Fei Tian and Tao Qin and Jianhuang Lai and Tie{-}Yan Liu},
  title           = {Adversarial Neural Machine Translation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1704.06933},
  url             = {http://arxiv.org/abs/1704.06933},
  keywords        = {nmt, gan},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WuXZTQLL17},
  timestamp       = {Wed, 07 Jun 2017 14:42:51 +0200}
}

@Article{wu2017-compact,
  author          = {Chunpeng Wu and Wei Wen and Tariq Afzal and Yongmei Zhang and Yiran Chen and Hai Li},
  title           = {A Compact {DNN:} Approaching Googlenet-Level Accuracy of Classification and Domain Adaptation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.04071},
  url             = {http://arxiv.org/abs/1703.04071},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/WuWAZCL17},
  timestamp       = {Mon, 03 Apr 2017 12:41:34 +0200}
}

@InCollection{wu2017-multiscale,
  author          = {Wu, Xiang and Guo, Ruiqi and Suresh, Ananda Theertha and Kumar, Sanjiv and Holtmann-Rice, Daniel N and Simcha, David
                  and Yu, Felix X},
  title           = {Multiscale Quantization for Fast Similarity Search},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems 30},
  editor          = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {5749--5757},
  url             = {http://papers.nips.cc/paper/7157-multiscale-quantization-for-fast-similarity-search.pdf}
}

@Article{wu2017-starspace,
  author          = {{Wu}, L. and {Fisch}, A. and {Chopra}, S. and {Adams}, K. and {Bordes}, A. and {Weston}, J.},
  title           = {{StarSpace: Embed All The Things!}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = sep,
  eprint          = {1709.03856},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL"
}

@InProceedings{wu2018-training,
  author          = {Shuang Wu and Guoqi Li and Feng Chen and Luping Shi},
  title           = {Training and Inference with Integers in Deep Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HJGXzmspb}
}

@Article{xia2017-dual,
  author          = {{Xia}, Y. and {Qin}, T. and {Chen}, W. and {Bian}, J. and {Yu}, N. and {Liu}, T.-Y.},
  title           = {{Dual Supervised Learning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.00415},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Statistics - Machine Learning},
  primaryclass    = "cs.LG"
}

@InProceedings{xiang2014-beyond,
  author          = {Xiang, Yu and Mottaghi, Roozbeh and Savarese, Silvio},
  title           = {Beyond pascal: A benchmark for 3d object detection in the wild},
  keywords        = {data, pascal},
  year            = 2014,
  booktitle       = {Applications of Computer Vision (WACV), 2014 IEEE Winter Conference on},
  organization    = {IEEE},
  pages           = {75--82},
  timestamp       = {20190102T0943}
}

@Article{xiao2018-dynamical,
  author          = {{Xiao}, L. and {Bahri}, Y. and {Sohl-Dickstein}, J. and {Schoenholz}, S.~S. and {Pennington}, J.},
  title           = {{Dynamical Isometry and a Mean Field Theory of Cnns: How To Train 10,000-layer Vanilla Convolutional Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jun,
  eprint          = {1806.05393},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180605393X},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Machine Learning},
  primaryclass    = "stat.ML",
  timestamp       = {20190203T1611}
}

@Article{xiao2018-generating,
  author          = {{Xiao}, C. and {Li}, B. and {Zhu}, J.-Y. and {He}, W. and {Liu}, M. and {Song}, D.},
  title           = {{Generating Adversarial Examples With Adversarial Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = jan,
  eprint          = {1801.02610},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180102610X},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack, advgan},
  primaryclass    = "cs.CR",
  timestamp       = {20190203T1611}
}

@InProceedings{xiao2018-spatially,
  author          = {Chaowei Xiao and Jun-Yan Zhu and Bo Li and Warren He and Mingyan Liu and Dawn Song},
  title           = {Spatially Transformed Adversarial Examples},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=HyydRMZC-}
}

@InProceedings{xie2017-adversarial,
  author          = {Xie, Cihang and Wang, Jianyu and Zhang, Zhishuai and Zhou, Yuyin and Xie, Lingxi and Yuille, Alan},
  title           = {Adversarial Examples for Semantic Segmentation and Object Detection},
  year            = 2017,
  booktitle       = {International Conference on Computer Vision},
  organization    = {IEEE},
  keywords        = {adversarial, attack, dag, dense adversarial generation}
}

@Article{xie2017-alibaba,
  author          = {Xie, Pengjun and others},
  title           = {Alibaba At Ijcnlp-2017 Task 1: Embedding Grammatical Features Into Lstms for Chinese Grammatical Error Diagnosis Task},
  journaltitle    = {Proceedings of the IJCNLP 2017, Shared Tasks},
  year            = 2017,
  pages           = {41--46},
  journal         = {Proceedings of the IJCNLP 2017, Shared Tasks}
}

@InProceedings{xie2017-constituent,
  author          = {Xie, Pengtao and Xing, Eric},
  title           = {A Constituent-Centric Neural Architecture for Reading Comprehension},
  year            = 2017,
  booktitle       = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  volume          = 1,
  pages           = {1405--1414}
}

@Article{xie2017-genetic,
  author          = {Lingxi Xie and Alan L. Yuille},
  title           = {Genetic {CNN}},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.01513},
  eprint          = {1703.01513},
  url             = {http://arxiv.org/abs/1703.01513},
  keywords        = {evolution, architecture},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/XieY17},
  timestamp       = {Wed, 07 Jun 2017 14:42:20 +0200}
}

@Article{xie2017-mitigating,
  author          = {Cihang Xie and Jianyu Wang and Zhishuai Zhang and Zhou Ren and Alan L. Yuille},
  title           = {Mitigating Adversarial Effects Through Randomization},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.01991},
  keywords        = {adversarial, defense},
  journal         = {CoRR}
}

@Article{xie2019-exploring,
  author          = {{Xie}, Saining and {Kirillov}, Alexander and {Girshick}, Ross and {He}, Kaiming},
  title           = {{Exploring Randomly Wired Neural Networks for Image Recognition}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1904.01569},
  month           = "Apr",
  pages           = {arXiv:1904.01569},
  eprint          = {1904.01569},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190401569X},
  archiveprefix   = {arXiv},
  keywords        = {nas, network generator},
  primaryclass    = {cs.CV},
  timestamp       = {20190419T1326}
}

@Article{xing2018-walk,
  author          = {{Xing}, C. and {Arpit}, D. and {Tsirigotis}, C. and {Bengio}, Y.},
  title           = {{A Walk With SGD}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.08770},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180208770X},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Learning},
  primaryclass    = "stat.ML"
}

@Article{xiong2017-deeppath,
  author          = {{Xiong}, W. and {Hoang}, T. and {Wang}, W.~Y.},
  title           = {{DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.06690},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {knowledge graph, embedding, reinforcement learning, kg, rl},
  primaryclass    = "cs.CL"
}

@Article{xiong2017-multi,
  author          = {{Xiong}, H. and {He}, Z. and {Hu}, X. and {Wu}, H.},
  title           = {{Multi-Channel Encoder for Neural Machine Translation}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = dec,
  eprint          = {1712.02109},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171202109X},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL"
}

@Article{xu2009-robustness,
  author          = {Xu, Huan and Caramanis, Constantine and Mannor, Shie},
  title           = {Robustness and Regularization of Support Vector Machines},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2009,
  volume          = 10,
  number          = {Jul},
  pages           = {1485--1510},
  journal         = {Journal of Machine Learning Research}
}

@InProceedings{xu2015-show,
  author          = {Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron C and Salakhutdinov, Ruslan and Zemel,
                  Richard S and Bengio, Yoshua},
  title           = {Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.},
  year            = 2015,
  booktitle       = {ICML},
  volume          = 14,
  pages           = {77--81}
}

@Article{xu2016-local,
  author          = {Juefei Xu and Vishnu Naresh Boddeti and Marios Savvides},
  title           = {Local Binary Convolutional Neural Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1608.06049},
  url             = {http://arxiv.org/abs/1608.06049},
  keywords        = {quantization, random, binary},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Juefei-XuBS16},
  timestamp       = {Wed, 07 Jun 2017 14:42:25 +0200}
}

@InProceedings{xu2018-alternating,
  author          = {Chen Xu and Jianqiang Yao and Zhouchen Lin and Wenwu Ou and Yuanbin Cao and Zhirong Wang and Hongbin Zha},
  title           = {Alternating Multi-bit Quantization for Recurrent Neural Networks},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=S19dR9x0b},
  keywords        = {quant}
}

@Article{yan2016-perspective,
  author          = {Xinchen Yan and Jimei Yang and Ersin Yumer and Yijie Guo and Honglak Lee},
  title           = {Perspective Transformer Nets: Learning Single-View 3d Object Reconstruction Without 3d Supervision},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1612.00814},
  eprint          = {1612.00814},
  url             = {http://arxiv.org/abs/1612.00814},
  keywords        = {ptn},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/YanYYGL16},
  timestamp       = {Mon, 13 Aug 2018 16:47:32 +0200}
}

@Book{yang2006-verb,
  author          = {Yang, Dongqiang and Powers, David Martin},
  title           = {Verb similarity on the taxonomy of WordNet},
  year            = 2006,
  publisher       = {Masaryk University},
  keywords        = {yp}
}

@Article{yang2014-deep,
  author          = {Zichao Yang and Marcin Moczulski and Misha Denil and Nando de Freitas and Alexander J. Smola and Le Song and Ziyu Wang},
  title           = {Deep Fried Convnets},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.7149},
  url             = {http://arxiv.org/abs/1412.7149},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/YangMDFSSW14},
  timestamp       = {Thu, 01 Jan 2015 19:51:08 +0100}
}

@Article{yang2015-stacked,
  author          = {Zichao Yang and Xiaodong He and Jianfeng Gao and Li Deng and Alexander J. Smola},
  title           = {Stacked Attention Networks for Image Question Answering},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1511.02274},
  url             = {http://arxiv.org/abs/1511.02274},
  journal         = {CoRR},
  timestamp       = {Wed, 07 Jun 2017 14:41:59 +0200}
}

@InProceedings{yang2015-weakly,
  author          = {Yang, Jimei and Reed, Scott E and Yang, Ming-Hsuan and Lee, Honglak},
  title           = {Weakly-supervised disentangling with recurrent transformations for 3d view synthesis},
  keywords        = {disentangle},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {1099--1107},
  timestamp       = {20190110T0926}
}

@Article{yang2016-designing,
  author          = {Yang, Tien-Ju and Chen, Yu-Hsin and Sze, Vivienne},
  title           = {Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning},
  journaltitle    = {arXiv preprint arXiv:1611.05128},
  year            = 2016,
  keywords        = {pruning},
  journal         = {arXiv preprint arXiv:1611.05128}
}

@Article{yang2016-trace,
  author          = {Yongxin Yang and Timothy M. Hospedales},
  title           = {Trace Norm Regularised Deep Multi-Task Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1606.04038},
  eprint          = {1606.04038},
  url             = {http://arxiv.org/abs/1606.04038},
  keywords        = {multi-task, soft-sharing},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/YangH16a},
  timestamp       = {Wed, 07 Jun 2017 14:42:54 +0200}
}

@Article{yang2017-breaking,
  author          = {Yang, Zhilin and Dai, Zihang and Salakhutdinov, Ruslan and Cohen, William W},
  title           = {Breaking the Softmax Bottleneck: a High-Rank Rnn Language Model},
  journaltitle    = {arXiv preprint arXiv:1711.03953},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1711.03953}
}

@Article{yang2017-improving,
  author          = {Yang, Zhen and Chen, Wei and Wang, Feng and Xu, Bo},
  title           = {Improving Neural Machine Translation With Conditional Sequence Generative Adversarial Nets},
  journaltitle    = {arXiv preprint arXiv:1703.04887},
  year            = 2017,
  keywords        = {nmt},
  journal         = {arXiv preprint arXiv:1703.04887}
}

@Article{yannakakis2015-panorama,
  author          = {G. N. Yannakakis and J. Togelius},
  title           = {A Panorama of Artificial and Computational Intelligence in Games},
  journaltitle    = {IEEE Transactions on Computational Intelligence and AI in Games},
  year            = 2015,
  volume          = 7,
  number          = 4,
  month           = {Dec},
  pages           = {317-335},
  issn            = {1943-068X},
  doi             = {10.1109/TCIAIG.2014.2339221},
  journal         = {IEEE Transactions on Computational Intelligence and AI in Games}
}

@Article{yao1999-evolving,
  author          = {Xin Yao},
  title           = {Evolving Artificial Neural Networks},
  journaltitle    = {Proceedings of the IEEE},
  year            = 1999,
  volume          = 87,
  number          = 9,
  month           = {Sep},
  pages           = {1423-1447},
  issn            = {0018-9219},
  doi             = {10.1109/5.784219},
  journal         = {Proceedings of the IEEE},
  keywords        = {genetic, evolutionary, survey}
}

@Article{yao2017-automated,
  author          = {Yuanshun Yao and Bimal Viswanath and Jenna Cryan and Haitao Zheng and Ben Y. Zhao},
  title           = {Automated Crowdturfing Attacks and Defenses in Online Review Systems},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1708.08151},
  keywords        = {adversarial, attack, defense, txt},
  journal         = {CoRR}
}

@Article{yedidia2005-constructing,
  author          = {Yedidia, Jonathan S and Freeman, William T and Weiss, Yair},
  title           = {Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms},
  journaltitle    = {IEEE Transactions on Information Theory},
  year            = 2005,
  volume          = 51,
  number          = 7,
  pages           = {2282--2312},
  journal         = {IEEE Transactions on Information Theory},
  publisher       = {IEEE}
}

@InCollection{yin2018-dimensionality,
  author          = {Yin, Zi and Shen, Yuanyuan},
  title           = {On the Dimensionality of Word Embedding},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {894--905},
  url             = {http://papers.nips.cc/paper/7368-on-the-dimensionality-of-word-embedding.pdf},
  timestamp       = {20181204T1504}
}

@Article{yogatama2017-generative,
  author          = {{Yogatama}, D. and {Dyer}, C. and {Ling}, W. and {Blunsom}, P.},
  title           = {{Generative and Discriminative Text Classification With Recurrent Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = mar,
  eprint          = {1703.01898},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv170301898Y},
  archiveprefix   = "arXiv",
  keywords        = {Statistics - Machine Learning, Computer Science - Computation and Language, Computer Science - Learning},
  primaryclass    = "stat.ML"
}

@Article{yogatama2017-learning,
  author          = {Yogatama, Dani and Blunsom, Phil and Dyer, Chris and Grefenstette, Edward and Ling, Wang},
  title           = {Learning To Compose Words Into Sentences With Reinforcement Learning},
  journaltitle    = {International Conference on Learning Representations},
  year            = 2017,
  journal         = {International Conference on Learning Representations},
  timestamp       = {20190108T0839}
}

@Article{yosinski2014-how,
  author          = {Jason Yosinski and Jeff Clune and Yoshua Bengio and Hod Lipson},
  title           = {How Transferable Are Features in Deep Neural Networks?},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1411.1792},
  url             = {http://arxiv.org/abs/1411.1792},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/YosinskiCBL14},
  timestamp       = {Mon, 01 Dec 2014 14:32:13 +0100}
}

@Article{yosinski2015-understanding,
  author          = {Yosinski, Jason and Clune, Jeff and Nguyen, Anh and Fuchs, Thomas and Lipson, Hod},
  title           = {Understanding Neural Networks Through Deep Visualization},
  journaltitle    = {arXiv preprint arXiv:1506.06579},
  year            = 2015,
  journal         = {arXiv preprint arXiv:1506.06579},
  timestamp       = {20181223T1253}
}

@Article{you2017-imagenet,
  author          = {Yang You and Zhao Zhang and Cho{-}Jui Hsieh and James Demmel},
  title           = {100-epoch Imagenet Training With Alexnet in 24 Minutes},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1709.05011},
  journal         = {CoRR},
  timestamp       = {20181223T1253}
}

@Article{yu2015-lsun,
  author          = {Fisher Yu and Yinda Zhang and Shuran Song and Ari Seff and Jianxiong Xiao},
  title           = {{LSUN:} Construction of a Large-Scale Image Dataset Using Deep Learning With Humans in the Loop},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.03365},
  eprint          = {1506.03365},
  url             = {http://arxiv.org/abs/1506.03365},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/YuZSSX15},
  keywords        = {data, lsun},
  timestamp       = {20181223T1252}
}

@Article{yu2016-seqgan,
  author          = {Lantao Yu and Weinan Zhang and Jun Wang and Yong Yu},
  title           = {Seqgan: Sequence Generative Adversarial Nets With Policy Gradient},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1609.05473},
  url             = {http://arxiv.org/abs/1609.05473},
  journal         = {CoRR},
  timestamp       = {Wed, 07 Jun 2017 14:40:58 +0200}
}

@Article{yu2017-normalized,
  author          = {{Yu}, A.~W. and {Lin}, Q. and {Salakhutdinov}, R. and {Carbonell}, J.},
  title           = {{Normalized Gradient With Adaptive Stepsize Method for Deep Neural Network Training}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.04822},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Artificial Intelligence},
  primaryclass    = "cs.LG"
}

@Article{yuan2006-model,
  author          = {Yuan, Ming and Lin, Yi},
  title           = {Model Selection and Estimation in Regression With Grouped Variables},
  journaltitle    = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
  year            = 2006,
  volume          = 68,
  number          = 1,
  pages           = {49--67},
  journal         = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
  publisher       = {Wiley Online Library}
}

@InProceedings{yuan2014-droid,
  author          = {Yuan, Zhenlong and Lu, Yongqiang and Wang, Zhaoguo and Xue, Yibo},
  title           = {Droid-sec: Deep learning in android malware detection},
  year            = 2014,
  booktitle       = {ACM SIGCOMM Computer Communication Review},
  volume          = 44,
  number          = 4,
  organization    = {ACM},
  pages           = {371--372}
}

@Article{yuan2017-adversarial,
  author          = {Yuan, Xiaoyong and He, Pan and Zhu, Qile and Li, Xiaolin},
  title           = {{Adversarial Examples: Attacks and Defenses for Deep Learning}},
  journaltitle    = {arXiv preprint},
  year            = 2017,
  doi             = {arXiv preprint arXiv:1712.07107},
  url             = {https://doi.org/arXiv preprint arXiv:1712.07107},
  journal         = {arXiv preprint},
  arxivid         = {1712.07107},
  keywords        = {Index Terms-deep neural network, adversarial examples, deep learning, security},
  timestamp       = {20190130T1708}
}

@Article{zachary2015-critical,
  author          = {Zachary C. Lipton, John Berkowitz, Charles Elkan},
  title           = {A Critical Review of Recurrent Neural Networks for Sequence Learning},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1506.00019},
  url             = {http://arxiv.org/abs/1506.00019},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/Lipton15},
  timestamp       = {Wed, 01 Jul 2015 15:10:24 +0200}
}

@Article{zantedeschi2017-efficient,
  author          = {{Zantedeschi}, V. and {Nicolae}, M.-I. and {Rawat}, A.},
  title           = {{Efficient Defenses Against Adversarial Attacks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = jul,
  eprint          = {1707.06728},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "cs.LG"
}

@Article{zaremba2014-learning,
  author          = {Wojciech Zaremba and Karol Kurach and Rob Fergus},
  title           = {Learning To Discover Efficient Mathematical Identities},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1406.1584},
  url             = {http://arxiv.org/abs/1406.1584},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ZarembaKF14},
  timestamp       = {Tue, 01 Jul 2014 11:58:08 +0200}
}

@Article{zaremba2014-learning-1,
  author          = {Wojciech Zaremba and Ilya Sutskever},
  title           = {Learning To Execute},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1410.4615},
  url             = {http://arxiv.org/abs/1410.4615},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ZarembaS14},
  timestamp       = {Sun, 02 Nov 2014 11:25:59 +0100}
}

@Article{zaremba2014-recurrent,
  author          = {Wojciech Zaremba and Ilya Sutskever and Oriol Vinyals},
  title           = {Recurrent Neural Network Regularization},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1409.2329},
  url             = {http://arxiv.org/abs/1409.2329},
  keywords        = {rnn, regularization},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ZarembaSV14},
  timestamp       = {Wed, 01 Oct 2014 15:00:04 +0200}
}

@Article{zaremba2015-learning,
  author          = {{Zaremba}, W. and {Mikolov}, T. and {Joulin}, A. and {Fergus}, R.},
  title           = {{Learning Simple Algorithms From Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2015,
  month           = nov,
  eprint          = {1511.07275},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Artificial Intelligence, Computer Science - Learning},
  primaryclass    = "cs.AI"
}

@Article{zdeborova2008-locked,
  author          = {Zdeborov{\'a}, Lenka and M{\'e}zard, Marc},
  title           = {Locked Constraint Satisfaction Problems},
  journaltitle    = {Physical review letters},
  year            = 2008,
  volume          = 101,
  number          = 7,
  pages           = 078702,
  journal         = {Physical review letters},
  publisher       = {APS}
}

@InProceedings{zeiler2010-deconvolutional,
  author          = {Zeiler, Matthew D and Krishnan, Dilip and Taylor, Graham W and Fergus, Rob},
  title           = {Deconvolutional networks},
  year            = 2010,
  booktitle       = {Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on},
  organization    = {IEEE},
  pages           = {2528--2535}
}

@Article{zeiler2013-visualizing,
  author          = {Matthew D. Zeiler and Rob Fergus},
  title           = {Visualizing and Understanding Convolutional Networks},
  journaltitle    = {CoRR},
  year            = 2013,
  volume          = {abs/1311.2901},
  keywords        = {interpret, zfnet},
  journal         = {CoRR}
}

@Article{zenke2017-superspike,
  author          = {{Zenke}, F. and {Ganguli}, S.},
  title           = {{SuperSpike: Supervised Learning in Multi-Layer Spiking Neural networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = may,
  eprint          = {1705.11146},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Quantitative Biology - Neurons and Cognition, Computer Science - Learning, Computer Science - Neural and Evolutionary
                  Computing, Statistics - Machine Learning},
  primaryclass    = "q-bio.NC"
}

@Article{zhang1993-evolving,
  author          = {Zhang, Byoung-Tak and Muhlenbein, Heinz},
  title           = {Evolving Optimal Neural Networks Using Genetic Algorithms With Occam's Razor},
  journaltitle    = {Complex systems},
  year            = 1993,
  volume          = 7,
  number          = 3,
  pages           = {199--220},
  journal         = {Complex systems},
  publisher       = {[Champaign, IL, USA: Complex Systems Publications, Inc., c1987-}
}

@Article{zhang2000-neural,
  author          = {Zhang, G.P.},
  title           = {Neural Networks for Classification: a Survey},
  journaltitle    = {Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on},
  year            = 2000,
  volume          = 30,
  number          = 4,
  month           = {Nov},
  pages           = {451-462},
  issn            = {1094-6977},
  doi             = {10.1109/5326.897072},
  journal         = {Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on},
  keywords        = {survey, generalisation (artificial intelligence);learning (artificial intelligence);neural nets;pattern
                  classification;classification;conventional classifiers;feature variable
                  selection;generalization;learning;misclassification costs;neural classifiers;neural networks;posterior probability
                  estimation;Costs;Decision making;Humans;Input variables;Medical diagnosis;Medical diagnostic imaging;Network
                  synthesis;Neural networks;Probability;Speech recognition}
}

@InProceedings{zhang2005-k,
  author          = {Zhang, Min-Ling and Zhou, Zhi-Hua},
  title           = {A K-Nearest Neighbor Based Algorithm for Multi-Label Classification},
  year            = 2005,
  booktitle       = {2005 IEEE international conference on granular computing},
  volume          = 2,
  organization    = {IEEE},
  pages           = {718--721}
}

@InCollection{zhang2015-active,
  author          = {Zhang, Chicheng and Chaudhuri, Kamalika},
  title           = {Active Learning from Weak and Strong Labelers},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {703--711},
  url             = {http://papers.nips.cc/paper/5988-active-learning-from-weak-and-strong-labelers.pdf}
}

@InCollection{zhang2015-character,
  author          = {Zhang, Xiang and Zhao, Junbo and LeCun, Yann},
  title           = {Character-level Convolutional Networks for Text Classification},
  year            = 2015,
  booktitle       = {Advances in Neural Information Processing Systems 28},
  editor          = {C. Cortes and N. D. Lawrence and D. D. Lee and M. Sugiyama and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {649--657},
  url             = {http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classification.pdf},
  keywords        = {charcnn}
}

@InProceedings{zhang2015-efficient,
  author          = {Zhang, Xiangyu and Zou, Jianhua and Ming, Xiang and He, Kaiming and Sun, Jian},
  title           = {Efficient and accurate approximations of nonlinear convolutional networks},
  year            = 2015,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {1984--1992}
}

@Article{zhang2015-feedforward,
  author          = {Shiliang Zhang and Cong Liu and Hui Jiang and Si Wei and Li{-}Rong Dai and Yu Hu},
  title           = {Feedforward Sequential Memory Networks: {A} New Structure To Learn Long-Term Dependency},
  journaltitle    = {CoRR},
  year            = 2015,
  volume          = {abs/1512.08301},
  journal         = {CoRR}
}

@Article{zhang2016-architectural,
  author          = {{Zhang}, S. and {Wu}, Y. and {Che}, T. and {Lin}, Z. and {Memisevic}, R. and {Salakhutdinov}, R. and {Bengio}, Y.},
  title           = {{Architectural Complexity Measures of Recurrent Neural Networks}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = feb,
  eprint          = {1602.08210},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning, Computer Science - Neural and Evolutionary Computing},
  primaryclass    = "cs.LG"
}

@Article{zhang2016-understanding,
  author          = {Zhang, Chiyuan and Bengio, Samy and Hardt, Moritz and Recht, Benjamin and Vinyals, Oriol},
  title           = {Understanding Deep Learning Requires Rethinking Generalization},
  journaltitle    = {arXiv preprint arXiv:1611.03530},
  year            = 2016,
  keywords        = {generalization, sgd, regularization},
  journal         = {arXiv preprint arXiv:1611.03530}
}

@Article{zhang2017-deconvolutional,
  author          = {Yizhe Zhang and Dinghan Shen and Guoyin Wang and Zhe Gan and Ricardo Henao and Lawrence Carin},
  title           = {Deconvolutional Paragraph Representation Learning},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1708.04729},
  journal         = {CoRR}
}

@InProceedings{zhang2017-prior,
  author          = {Zhang, Jiacheng and Liu, Yang and Luan, Huanbo and Xu, Jingfang and Sun, Maosong},
  title           = {Prior knowledge integration for neural machine translation using posterior regularization},
  year            = 2017,
  booktitle       = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  volume          = 1,
  pages           = {1514--1523},
  keywords        = {nmt}
}

@Article{zhang2017-which,
  author          = {Zhang, Xiang and LeCun, Yann},
  title           = {Which Encoding Is the Best for Text Classification in Chinese, English, Japanese and Korean?},
  journaltitle    = {arXiv preprint arXiv:1708.02657},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1708.02657}
}

@Article{zhang2018-byte,
  author          = {{Zhang}, X. and {LeCun}, Y.},
  title           = {{Byte-Level Recursive Convolutional Auto-Encoder for Text}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = feb,
  eprint          = {1802.01817},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180201817Z},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Computation and Language},
  primaryclass    = "cs.CL"
}

@InProceedings{zhang2018-discrimination,
  author          = {Pengchuan Zhang and Qiang Liu and Dengyong Zhou and Tao Xu and Xiaodong He},
  title           = {On the Discrimination-Generalization Tradeoff in {GAN}s},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=Hk9Xc_lR-}
}

@InCollection{zhang2018-learning,
  author          = {Zhang, Xiuming and Zhang, Zhoutong and Zhang, Chengkai and Tenenbaum, Josh and Freeman, Bill and Wu, Jiajun},
  title           = {Learning to Reconstruct Shapes from Unseen Classes},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems 31},
  editor          = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
  publisher       = {Curran Associates, Inc.},
  pages           = {2263--2274},
  url             = {http://papers.nips.cc/paper/7494-learning-to-reconstruct-shapes-from-unseen-classes.pdf},
  timestamp       = {20181207T1047}
}

@InProceedings{zhao2011-image,
  author          = {Zhao, Yibiao and Zhu, Song-Chun},
  title           = {Image parsing with stochastic scene grammar},
  year            = 2011,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {73--81},
  timestamp       = {20190104T0910}
}

@Article{zhao2016-energy,
  author          = {{Zhao}, J. and {Mathieu}, M. and {LeCun}, Y.},
  title           = {{Energy-Based Generative Adversarial Network}},
  journaltitle    = {ArXiv e-prints},
  year            = 2016,
  month           = sep,
  eprint          = {1609.03126},
  journal         = {ArXiv e-prints},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Learning},
  primaryclass    = "cs.LG"
}

@Article{zhao2017-adversarially,
  author          = {Junbo Jake Zhao and Yoon Kim and Kelly Zhang and Alexander M. Rush and Yann LeCun},
  title           = {Adversarially Regularized Autoencoders for Generating Discrete Structures},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1706.04223},
  eprint          = {1706.04223},
  url             = {http://arxiv.org/abs/1706.04223},
  keywords        = {gan, discrete},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/ZhaoKZRL17},
  timestamp       = {Mon, 03 Jul 2017 13:29:02 +0200}
}

@Article{zhao2017-generating,
  author          = {{Zhao}, Z. and {Dua}, D. and {Singh}, S.},
  title           = {{Generating Natural Adversarial Examples}},
  journaltitle    = {ArXiv e-prints},
  year            = 2017,
  month           = oct,
  eprint          = {1710.11342},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2017arXiv171011342Z},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, attack, img, txt, nmt, entailment},
  primaryclass    = "cs.LG"
}

@Article{zheng2018-distributionally,
  author          = {{Zheng}, T. and {Chen}, C. and {Ren}, K.},
  title           = {{Distributionally Adversarial Attack}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = aug,
  eprint          = {1808.05537},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180805537Z},
  archiveprefix   = "arXiv",
  keywords        = {Computer Science - Machine Learning, Computer Science - Cryptography and Security, Statistics - Machine Learning}
}

@Article{zhou2014-object,
  author          = {Bolei Zhou and Aditya Khosla and {\`A}gata Lapedriza and Aude Oliva and Antonio Torralba},
  title           = {Object Detectors Emerge in Deep Scene Cnns},
  journaltitle    = {CoRR},
  year            = 2014,
  volume          = {abs/1412.6856},
  url             = {http://arxiv.org/abs/1412.6856},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ZhouKLOT14},
  timestamp       = {Thu, 01 Jan 2015 19:51:08 +0100}
}

@Article{zhou2016-dorefa,
  author          = {Zhou, Shuchang and Wu, Yuxin and Ni, Zekun and Zhou, Xinyu and Wen, He and Zou, Yuheng},
  title           = {Dorefa-Net: Training Low Bitwidth Convolutional Neural Networks With Low Bitwidth Gradients},
  journaltitle    = {arXiv preprint arXiv:1606.06160},
  year            = 2016,
  keywords        = {quantization},
  journal         = {arXiv preprint arXiv:1606.06160}
}

@InProceedings{zhou2016-learning,
  author          = {Zhou, Bolei and Khosla, Aditya and Lapedriza, Agata and Oliva, Aude and Torralba, Antonio},
  title           = {Learning deep features for discriminative localization},
  year            = 2016,
  booktitle       = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages           = {2921--2929},
  keywords        = {cam, class activation map}
}

@InProceedings{zhou2016-less,
  author          = {Zhou, Hao and Alvarez, Jose M and Porikli, Fatih},
  title           = {Less is more: Towards compact cnns},
  year            = 2016,
  booktitle       = {European Conference on Computer Vision},
  organization    = {Springer},
  pages           = {662--677},
  keywords        = {pruning}
}

@Article{zhou2017-atrank,
  author          = {Chang Zhou and Jinze Bai and Junshuai Song and Xiaofei Liu and Zhengchao Zhao and Xiusi Chen and Jun Gao},
  title           = {Atrank: An Attention-Based User Behavior Modeling Framework for Recommendation},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1711.06632},
  journal         = {CoRR}
}

@Article{zhou2017-deep,
  author          = {Zhi{-}Hua Zhou and Ji Feng},
  title           = {Deep Forest: Towards An Alternative To Deep Neural Networks},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1702.08835},
  url             = {http://arxiv.org/abs/1702.08835},
  keywords        = {gcforest, representation learning, random},
  journal         = {CoRR},
  timestamp       = {Wed, 07 Jun 2017 14:40:23 +0200}
}

@Article{zhou2018-breaking,
  author          = {{Zhou}, Y. and {Kantarcioglu}, M. and {Xi}, B.},
  title           = {{Breaking Transferability of Adversarial Samples With Randomness}},
  journaltitle    = {ArXiv e-prints},
  year            = 2018,
  month           = may,
  eprint          = {1805.04613},
  journal         = {ArXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {http://adsabs.harvard.edu/abs/2018arXiv180504613Z},
  archiveprefix   = "arXiv",
  keywords        = {adversarial, defense},
  primaryclass    = "cs.CR"
}

@Article{zhu2007-stochastic,
  author          = {Zhu, Song-Chun and Mumford, David and others},
  title           = {A Stochastic Grammar of Images},
  journaltitle    = {Foundations and Trends{\textregistered} in Computer Graphics and Vision},
  year            = 2007,
  volume          = 2,
  number          = 4,
  pages           = {259--362},
  journal         = {Foundations and Trends{\textregistered} in Computer Graphics and Vision},
  publisher       = {Now Publishers, Inc.},
  timestamp       = {20190102T0947}
}

@InProceedings{zhu2008-unsupervised,
  author          = {Zhu, Long Leo and Lin, Chenxi and Huang, Haoda and Chen, Yuanhao and Yuille, Alan},
  title           = {Unsupervised structure learning: Hierarchical recursive composition, suspicious coincidence and competitive exclusion},
  year            = 2008,
  booktitle       = {European Conference on Computer Vision},
  organization    = {Springer},
  pages           = {759--773},
  timestamp       = {20190102T1634}
}

@Article{zhu2016-trained,
  author          = {Zhu, Chenzhuo and Han, Song and Mao, Huizi and Dally, William J},
  title           = {Trained Ternary Quantization},
  journaltitle    = {arXiv preprint arXiv:1612.01064},
  year            = 2016,
  keywords        = {quantization, ternary},
  journal         = {arXiv preprint arXiv:1612.01064}
}

@Article{zhu2017-unpaired,
  author          = {Jun{-}Yan Zhu and Taesung Park and Phillip Isola and Alexei A. Efros},
  title           = {Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1703.10593},
  url             = {http://arxiv.org/abs/1703.10593},
  keywords        = {cyclegan},
  journal         = {CoRR},
  timestamp       = {Wed, 07 Jun 2017 14:40:17 +0200}
}

@Article{zhu2018-remarkable,
  author          = {Liping Zhu and Song-Ju Kim and Masahiko Hara and Masashi Aono},
  title           = {Remarkable Problem-Solving Ability of Unicellular Amoeboid Organism and Its Mechanism},
  keywords        = {bio, amoeba, tsp},
  journaltitle    = {Royal Society Open Science},
  year            = 2018,
  volume          = 5,
  number          = 12,
  pages           = 180396,
  doi             = {10.1098/rsos.180396},
  eprint          = {https://royalsocietypublishing.org/doi/pdf/10.1098/rsos.180396},
  url             = {https://doi.org/10.1098/rsos.180396},
  journal         = {Royal Society Open Science},
  timestamp       = {20181225T0837}
}

@InProceedings{ziebart2008-maximum,
  author          = {Ziebart, Brian D and Maas, Andrew L and Bagnell, J Andrew and Dey, Anind K},
  title           = {Maximum Entropy Inverse Reinforcement Learning.},
  year            = 2008,
  booktitle       = {AAAI},
  pages           = {1433--1438},
  keywords        = {rl}
}

@Article{zilly2016-recurrent,
  author          = {Julian G. Zilly and Rupesh Kumar Srivastava and Jan Koutn{\'{\i}}k and J{\"{u}}rgen Schmidhuber},
  title           = {Recurrent Highway Networks},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1607.03474},
  eprint          = {1607.03474},
  url             = {http://arxiv.org/abs/1607.03474},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/ZillySKS16},
  timestamp       = {Wed, 07 Jun 2017 14:43:15 +0200}
}

@Article{zimek2012-survey,
  author          = {Zimek, Arthur and Schubert, Erich and Kriegel, Hans-Peter},
  title           = {A Survey on Unsupervised Outlier Detection in High-Dimensional Numerical Data},
  journaltitle    = {Stat. Anal. Data Min.},
  year            = 2012,
  volume          = 5,
  number          = 5,
  month           = oct,
  pages           = {363--387},
  issn            = {1932-1864},
  doi             = {10.1002/sam.11161},
  url             = {https://doi.org/10.1002/sam.11161},
  journal         = {Stat. Anal. Data Min.},
  acmid           = 2388917,
  address         = {New York, NY, USA},
  issue_date      = {October 2012},
  keywords        = {anomalies in high-dimensional data, approximate outlier detection, correlation outlier detection, curse of
                  dimensionality, outlier detection in high-dimensional data, subspace outlier detection},
  numpages        = 25,
  publisher       = {John Wiley \& Sons, Inc.}
}

@InProceedings{zolna2018-fraternal,
  author          = {Konrad Zolna and Devansh Arpit and Dendi Suhubdy and Yoshua Bengio},
  title           = {Fraternal Dropout},
  year            = 2018,
  booktitle       = {International Conference on Learning Representations},
  url             = {https://openreview.net/forum?id=SJyVzQ-C-}
}

@Article{zoph2016-neural,
  author          = {Barret Zoph and Quoc V. Le},
  title           = {Neural Architecture Search With Reinforcement Learning},
  journaltitle    = {CoRR},
  year            = 2016,
  volume          = {abs/1611.01578},
  url             = {http://arxiv.org/abs/1611.01578},
  journal         = {CoRR},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.uni-trier.de/rec/bib/journals/corr/ZophL16},
  keywords        = {architectures, evolution, rl, nas},
  timestamp       = {Thu, 01 Dec 2016 19:32:08 +0100}
}

@Article{zoph2017-learning,
  author          = {Barret Zoph and Vijay Vasudevan and Jonathon Shlens and Quoc V. Le},
  title           = {Learning Transferable Architectures for Scalable Image Recognition},
  journaltitle    = {CoRR},
  year            = 2017,
  volume          = {abs/1707.07012},
  eprint          = {1707.07012},
  url             = {http://arxiv.org/abs/1707.07012},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, http://dblp.org},
  biburl          = {http://dblp.org/rec/bib/journals/corr/ZophVSL17},
  keywords        = {evolution, rl, transfer, 500 gpu, nas, topology},
  timestamp       = {Sat, 05 Aug 2017 14:56:05 +0200}
}

@Article{mishra2019-gan,
  author          = {{Mishra}, Saumitra and {Stoller}, Daniel and {Benetos}, Emmanouil and {Sturm}, Bob L. and {Dixon}, Simon},
  title           = {{GAN-Based Generation and Automatic Selection of Explanations for Neural Networks}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1904.09533},
  month           = "Apr",
  pages           = {arXiv:1904.09533},
  eprint          = {1904.09533},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190409533M},
  archiveprefix   = {arXiv},
  keywords        = {Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and
                  Speech Processing, Statistics - Machine Learning},
  primaryclass    = {cs.LG},
  timestamp       = {20190430T1247}
}

@InProceedings{turian2010-word,
  author          = {Turian, Joseph and Ratinov, Lev and Bengio, Yoshua},
  title           = {Word representations: a simple and general method for semi-supervised learning},
  year            = 2010,
  booktitle       = {Proceedings of the 48th annual meeting of the association for computational linguistics},
  organization    = {Association for Computational Linguistics},
  pages           = {384--394},
  timestamp       = {20190606T1855}
}

@Article{razavi2019-generating,
  author          = {{Razavi}, Ali and {van den Oord}, Aaron and {Vinyals}, Oriol},
  title           = {{Generating Diverse High-Fidelity Images With VQ-VAE-2}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1906.00446},
  month           = "Jun",
  pages           = {arXiv:1906.00446},
  eprint          = {1906.00446},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190600446R},
  archiveprefix   = {arXiv},
  keywords        = {gan},
  primaryclass    = {cs.LG},
  timestamp       = {20190607T1519}
}

@InProceedings{oord2017-neural,
  author          = {van den Oord, Aaron and Vinyals, Oriol and others},
  title           = {Neural discrete representation learning},
  year            = 2017,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {6306--6315},
  timestamp       = {20190607T1553}
}

@Article{chen2017-pixelsnail,
  author          = {Chen, Xi and Mishra, Nikhil and Rohaninejad, Mostafa and Abbeel, Pieter},
  title           = {Pixelsnail: an Improved Autoregressive Generative Model},
  keywords        = {gan, autoregressive},
  journaltitle    = {arXiv preprint arXiv:1712.09763},
  year            = 2017,
  journal         = {arXiv preprint arXiv:1712.09763},
  timestamp       = {20190607T1555}
}

@Article{ravuri2019-classification,
  author          = {{Ravuri}, Suman and {Vinyals}, Oriol},
  title           = {{Classification Accuracy Score for Conditional Generative Models}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1905.10887},
  month           = "May",
  pages           = {arXiv:1905.10887},
  eprint          = {1905.10887},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190510887R},
  archiveprefix   = {arXiv},
  keywords        = {cas},
  primaryclass    = {cs.LG},
  timestamp       = {20190607T1602}
}

@Article{real2018-regularized,
  author          = {Esteban Real and Alok Aggarwal and Yanping Huang and Quoc V. Le},
  title           = {Regularized Evolution for Image Classifier Architecture Search},
  keywords        = {nas, amoeba, evolution},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1802.01548},
  eprint          = {1802.01548},
  url             = {http://arxiv.org/abs/1802.01548},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1802-01548},
  timestamp       = {20190608T1110}
}

@Article{fetaya2019-conditional,
  author          = {{Fetaya}, Ethan and {Jacobsen}, J{\"o}rn-Henrik and {Zemel}, Richard},
  title           = {{Conditional Generative Models Are Not Robust}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1906.01171},
  month           = "Jun",
  pages           = {arXiv:1906.01171},
  eprint          = {1906.01171},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190601171F},
  archiveprefix   = {arXiv},
  keywords        = {Computer Science - Machine Learning, Statistics - Machine Learning},
  primaryclass    = {cs.LG},
  timestamp       = {20190609T1446}
}

@Article{schott2018-towards,
  author          = {Lukas Schott and Jonas Rauber and Wieland Brendel and Matthias Bethge},
  title           = {Towards the First Adversarially Robust Neural Network Model on Mnist},
  journaltitle    = {CoRR},
  year            = 2018,
  volume          = {abs/1805.09190},
  eprint          = {1805.09190},
  url             = {http://arxiv.org/abs/1805.09190},
  journal         = {CoRR},
  archiveprefix   = {arXiv},
  bibsource       = {dblp computer science bibliography, https://dblp.org},
  biburl          = {https://dblp.org/rec/bib/journals/corr/abs-1805-09190},
  timestamp       = {20190609T1449}
}

@Article{bachman2019-learning,
  author          = {{Bachman}, Philip and {Devon Hjelm}, R and {Buchwalter}, William},
  title           = {{Learning Representations By Maximizing Mutual Information Across Views}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1906.00910},
  month           = "Jun",
  pages           = {arXiv:1906.00910},
  eprint          = {1906.00910},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190600910B},
  archiveprefix   = {arXiv},
  keywords        = {lr, amdim},
  primaryclass    = {cs.LG},
  timestamp       = {20190610T1155}
}

@Article{gidaris2018-unsupervised,
  author          = {Gidaris, Spyros and Singh, Praveer and Komodakis, Nikos},
  title           = {Unsupervised Representation Learning By Predicting Image Rotations},
  keywords        = {lr},
  journaltitle    = {arXiv preprint arXiv:1803.07728},
  year            = 2018,
  journal         = {arXiv preprint arXiv:1803.07728},
  timestamp       = {20190610T1156}
}

@Article{elsken2019-neural,
  author          = {Thomas Elsken and Jan Hendrik Metzen and Frank Hutter},
  title           = {Neural Architecture Search: a Survey},
  keywords        = {nas, survey},
  journaltitle    = {Journal of Machine Learning Research},
  year            = 2019,
  volume          = 20,
  number          = 55,
  month           = apr,
  pages           = {1-21},
  journal         = {Journal of Machine Learning Research},
  timestamp       = {20190610T1317}
}

@InProceedings{santurkar2018-how,
  author          = {Santurkar, Shibani and Tsipras, Dimitris and Ilyas, Andrew and Madry, Aleksander},
  title           = {How does batch normalization help optimization?},
  keywords        = {bn},
  year            = 2018,
  booktitle       = {Advances in Neural Information Processing Systems},
  pages           = {2483--2493},
  timestamp       = {20190610T1521}
}

@Article{cubuk2017-intriguing,
  author          = {{Cubuk}, Ekin D. and {Zoph}, Barret and {Schoenholz}, Samuel S. and {Le}, Quoc V.},
  title           = {{Intriguing Properties of Adversarial Examples}},
  journaltitle    = {arXiv e-prints},
  year            = 2017,
  eid             = {arXiv:1711.02846},
  month           = "Nov",
  pages           = {arXiv:1711.02846},
  eprint          = {1711.02846},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2017arXiv171102846C},
  archiveprefix   = {arXiv},
  keywords        = {adversarial, nas},
  primaryclass    = {stat.ML},
  timestamp       = {20190610T1950}
}

@Article{ying2019-nas,
  author          = {Ying, Chris and Klein, Aaron and Real, Esteban and Christiansen, Eric and Murphy, Kevin and Hutter, Frank},
  title           = {Nas-Bench-101: Towards Reproducible Neural Architecture Search},
  keywords        = {nas},
  journaltitle    = {arXiv preprint arXiv:1902.09635},
  year            = 2019,
  journal         = {arXiv preprint arXiv:1902.09635},
  timestamp       = {20190611T1015}
}

@Article{zellers2019-defending,
  author          = {{Zellers}, Rowan and {Holtzman}, Ari and {Rashkin}, Hannah and {Bisk}, Yonatan and {Farhadi}, Ali and {Roesner},
                  Franziska and {Choi}, Yejin},
  title           = {{Defending Against Neural Fake News}},
  journaltitle    = {arXiv e-prints},
  year            = 2019,
  eid             = {arXiv:1905.12616},
  month           = "May",
  pages           = {arXiv:1905.12616},
  eprint          = {1905.12616},
  journal         = {arXiv e-prints},
  adsnote         = {Provided by the SAO/NASA Astrophysics Data System},
  adsurl          = {https://ui.adsabs.harvard.edu/abs/2019arXiv190512616Z},
  archiveprefix   = {arXiv},
  keywords        = {adversarial, text, grover},
  primaryclass    = {cs.CL},
  timestamp       = {20190611T1426}
}