README.md

summaries of papers on deep learning.

---

• [Week-1] 15-Oct-2017 - DL history and basics : DBN, AlexNet, VGGNet, GoogLeNet, ResNet, RNN(speech evolution)
• [Week-2] 22-Oct-2017 - DL methods : models, optimization, deep generative model, rnn/seq-to-seq model
• [Week-3] 29-Oct-2017 - DL methods : Neural Turing Machine,Reinforcement-Transfer-One-Shot Deep Learning
• [Week-4] 06-Nov-2017 - DL applications : nlp, object detection, visual tracking, image caption
• [Week-5] 12-Nov-2017 - DL applications : Machine Translation, Robotics, Art, Object Segmentation
• [Week-6] 19-Nov-2017 - recommender systems
• [Week-7] 26-Nov-2017 - ftm : 01/2011 - 12/2014
• [Week-8] 03-Dec-2017 - ftm : 01/2015 - 12/2015
• [Week-9] 10-Dec-2017 - ftm : 01/2016 - 05/2016
• [Week-10] 17-Dec-2017 - ftm : 06/2016 - 12/2016
• [Week-11] 24-Dec-2017 - ftm : 01/2017 - 07/2017
• [Week-12] 31-Dec-2017 - ftm : 08/2017 - 12/2017

---

• [Jan-2018]
• [Feb-2018]
• [March-2018]
• [April-2018]
• [May-2018]
• [June-2018]

Articles

• [Jan2March 2018]
• [April2June 2018]
• [2018 so far]
• [2018-Jan-Sep]
• [conferences-2018]

---

---

07/2019

• How Did Humans Become So Creative? A Computational Approach ⭐
• Deep Learning for Spacecraft Pose Estimation from Photorealistic Rendering
• Translating neural signals to text using a Brain-Machine Interface
• SVGD: A Virtual Gradients Descent Method for Stochastic Optimization
• A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends
• Large Memory Layers with Product Keys ⭐
• Large Scale Adversarial Representation Learning
• Regularizing Neural Networks for Future Trajectory Prediction via Inverse Reinforcement Learning
• Out-of-Distribution Detection Using Neural Rendering Generative Models
• City-GAN: Learning architectural styles using a custom Conditional GAN architecture
• Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
• Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
• A Review of Machine Learning Applications in Fuzzing
• GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering
• Machine Learning Kernel Method from a Quantum Generative Model
• A Neural Architecture for Designing Truthful and Efficient Auctions
• Fast geodesic shooting for landmark matching using CUDA
• The Role of Cooperation in Responsible AI Development
• PreCall: A Visual Interface for Threshold Optimization in ML Model Selection
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Playing Go without Game Tree Search Using Convolutional Neural Networks
• Incrementalizing RASA's Open-Source Natural Language Understanding Pipeline
• BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
• Making AI Forget You: Data Deletion in Machine Learning
• Explainable Machine Learning for Scientific Insights and Discoveries
• What does it mean to understand a neural network?
• Efficient Video Generation on Complex Datasets
• NPA: Neural News Recommendation with Personalized Attention
• Artificial Intelligence as a Services (AI-aaS) on Software-Defined Infrastructure
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Task Selection Policies for Multitask Learning
• Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation
• A Neural Turing~Machine for Conditional Transition Graph Modeling
• A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
• OCC: A Smart Reply System for Efficient In-App Communications
• A Survey of Data Quality Measurement and Monitoring Tools
• User-Interactive Machine Learning Model for Identifying Structural Relationships of Code Features
• ELG: An Event Logic Graph
• CraftAssist: A Framework for Dialogue-enabled Interactive Agents
• HAKE: Human Activity Knowledge Engine
• Probing Neural Network Comprehension of Natural Language Arguments
• Beyond Imitation: Generative and Variational Choreography via Machine Learning
• HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips ⭐
• Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors
• Compositional Deep Learning
• SentiMATE: Learning to play Chess through Natural Language Processing
• Convolutional Reservoir Computing for World Models
• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre
• Optuna: A Next-generation Hyperparameter Optimization Framework ⭐
• Speech2Face: Learning the Face Behind a Voice
• Semi-parametric Object Synthesis
• INS: An Interactive Chinese News Synthesis System
• Green AI ⭐
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• U4D: Unsupervised 4D Dynamic Scene Understanding
• How to Manipulate CNNs to Make Them Lie: the GradCAM Case
• SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications
• Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Benchmarking TPU, GPU, and CPU Platforms for Deep Learning
• Towards AutoML in the presence of Drift: first results
• RNNbow: Visualizing Learning via Backpropagation Gradients in Recurrent Neural Networks
• ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
• Deep Reinforcement Learning for Personalized Search Story Recommendation
• FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
• Towards meta-learning for multi-target regression problems
• A Benchmark on Tricks for Large-scale Image Retrieval

---

06/2019

• Tackling Climate Change with Machine Learning ⭐
• Mesh R-CNN
• Does Object Recognition Work for Everyone?
• Energy and Policy Considerations for Deep Learning in NLP
• An Introduction to Variational Autoencoders
• Text-based Editing of Talking-head Video
• A Multi-Pass GAN for Fluid Flow Super-Resolution
• IoT Network Security from the Perspective of Adversarial Deep Learning
• Deep learning for image segmentation-a short survey
• On the Realization of Compositionality in Neural Networks
• Butterfly Transform: An Efficient FFT Based Neural Architecture Design
• Automated Machine Learning: State-of-The-Art and Open Challenges
• Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
• Automated Machine Learning with Monte-Carlo Tree Search (Extended Version)
• Explain Yourself! Leveraging Language Models for Commonsense Reasoning
• Automatic Reparameterisation of Probabilistic Programs
• Modeling e-Learners' Cognitive and Metacognitive Strategy in Comparative Question Solving
• Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach
• KERMIT: Generative Insertion-Based Modeling for Sequences ⭐
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
• Is Deep Learning an RG Flow?
• What Does BERT Look At? An Analysis of BERT's Attention
• Quantizing deep convolutional networks for efficient inference: A whitepaper
• What Kind of Language Is Hard to Language-Model?
• Open Sesame: Getting Inside BERT's Linguistic Knowledge
• NAS-FCOS: Fast Neural Architecture Search for Object Detection
• DCEF: Deep Collaborative Encoder Framework for Unsupervised Clustering
• Continual and Multi-Task Architecture Search
• The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
• Hierarchical Imitation and Reinforcement Learning
• Jacobian Policy Optimizations
• Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
• A Bayesian Perspective on the Deep Image Prior
• COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
• Topology-Preserving Deep Image Segmentation
• The Replica Dataset: A Digital Replica of Indoor Spaces
• Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
• Is the winner really the best? A critical analysis of common research practice in biomedical image analysis competitions
• Butterfly Transform: An Efficient FFT Based Neural Architecture Design
• A Survey on Deep Learning Architectures for Image-based Depth Reconstruction
• Neural Spline Flows
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• Deep learning for molecular design - a review of the state of the art
• Kernelized Capsule Networks
• Unsupervised Representation Learning of DNA Sequences
• Image Captioning: Transforming Objects into Words
• Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
• Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks
• Fast Calculation of Probabilistic Power Flow: A Model-based Deep Learning Approach
• Machine Learning Approach to Earthquake Rupture Dynamics
• Stand-Alone Self-Attention in Vision Models
• Inverse Cooking: Recipe Generation from Food Images
• Large Scale Structure of Neural Network Loss Landscapes
• Generative Adversarial Networks: A Survey and Taxonomy ⭐
• Accelerating Neural ODEs with Spectral Elements
• Human Side of Tesla Autopilot: Exploration of Functional Vigilance in Real-World Human-Machine Collaboration
• Stand-Alone Self-Attention in Vision Models
• Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
• Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
• Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Task Agnostic Continual Learning via Meta Learning
• Show, Match and Segment: Joint Learning of Semantic Matching and Object Co-segmentation
• The Replica Dataset: A Digital Replica of Indoor Spaces
• XLNet: Generalized Autoregressive Pretraining for Language Understanding [code] ⭐
• Weight Agnostic Neural Networks
• Model Compression by Entropy Penalized Reparameterization
• Analyzing the Structure of Attention in a Transformer Language Model
• PyRobot: An Open-source Robotics Framework for Research and Benchmarking ⭐
• Explaining Reinforcement Learning to Mere Mortals: An Empirical Study
• EVDodge: Embodied AI For High-Speed Dodging On A Quadrotor Using Event Cameras
• Federated Learning for Emoji Prediction in a Mobile Keyboard
• Neural Volumes: Learning Dynamic Renderable Volumes from Images
• Discovery of Physics from Data: Universal Laws and Discrepancy Models
• Prune and Replace NAS
• The Functional Neural Process
• StoryGAN: A Sequential Conditional GAN for Story Visualization
• Large Scale Structure of Neural Network Loss Landscapes
• Coupled Graph Neural Networks for Predicting the Popularity of Online Content
• PaperRobot: Incremental Draft Generation of Scientific Ideas
• Meta-learning of textual representations
• Deep Set Prediction Networks
• Modern Deep Reinforcement Learning Algorithms
• Machine Learning Phase Transitions with a Quantum Processor
• ORRB -- OpenAI Remote Rendering Backend
• Inducing Syntactic Trees from BERT Representations
• We Need No Pixels: Video Manipulation Detection Using Stream Descriptors
• End-to-End Visual Speech Recognition for Small-Scale Datasets
• Eliciting Knowledge from Experts:Automatic Transcript Parsing for Cognitive Task Analysis
• A Power Efficient Artificial Neuron Using Superconducting Nanowires ⭐

---

05/2019

• AI Feynman: a Physics-Inspired Method for Symbolic Regression ⭐
• Defending Against Neural Fake News
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks [EfficientNet-PyTorch] ⭐
• Graph Representations for Higher-Order Logic and Theorem Proving
• Speech2Face: Learning the Face Behind a Voice
• VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
• Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting
• Video-to-Video Translation for Visual Speech Synthesis
• Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
• PyTorch-BigGraph: A Large-scale Graph Embedding System ⭐
• Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
• Provably Powerful Graph Networks
• Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network
• Pre-training Graph Neural Networks
• Unsupervised Learning from Video with Deep Neural Embeddings
• Discrete Infomax Codes for Meta-Learning
• Few-Shot Adversarial Learning of Realistic Neural Talking Head Models ⭐
• Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation
• Adversarial Examples Are Not Bugs, They Are Features
• On Variational Bounds of Mutual Information
• How Does Batch Normalization Help Optimization?
• Solving NP-Hard Problems on Graphs by Reinforcement Learning without Domain Knowledge
• Object Discovery with a Copy-Pasting GAN
• Towards Neural Decompilation
• Multi-Sample Dropout for Accelerated Training and Better Generalization
• Discrete Flows: Invertible Generative Models of Discrete Data
• Kervolutional Neural Networks
• Deep Scale-spaces: Equivariance Over Scale
• Unified Language Model Pre-training for Natural Language Understanding and Generation
• Graph Matching Networks for Learning the Similarity of Graph Structured Objects
• Embedding Human Knowledge in Deep Neural Network via Attention Map
• The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
• Object Detection in 20 Years: A Survey ⭐
• Brain-mediated Transfer Learning of Convolutional Neural Networks
• Evolving Rewards to Automate Reinforcement Learning
• FastSpeech: Fast, Robust and Controllable Text to Speech
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Magic: The Gathering is Turing Complete
• SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver [code]
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• Challenges of Real-World Reinforcement Learning
• Meta reinforcement learning as task inference
• Accelerating Proposal Generation Network for \Fast Face Detection on Mobile Devices
• Go-Explore: a New Approach for Hard-Exploration Problems
• Finding Friend and Foe in Multi-Agent Games
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud
• Examining Structure of Word Embeddings with PCA
• Defending Against Neural Fake News
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Consensus Clustering: An Embedding Perspective, Extension and Beyond
• RAPID: Early Classification of Explosive Transients using Deep Learning

---

04/2019

• A Systematic Literature Review about the impact of Artificial Intelligence on Autonomous Vehicle Safety
• Analysing Mathematical Reasoning Abilities of Neural Models. https://arxiv.org/pdf/1904.01557v1.pdf deepmind/mathematics_dataset
• Libra R-CNN: Towards Balanced Learning for Object Detection
• YOLACT: Real-time Instance Segmentation
• Advancing NLP with Cognitive Language Processing Signals
• Visualizing Attention in Transformer-Based Language models
• Recommendations for Datasets for Source Code Summarization
• An End-to-End Baseline for Video Captioning
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Hyperbolic Image Embeddings
• PaintBot: A Reinforcement Learning Approach for Natural Media Painting
• Reducing BERT Pre-Training Time from 3 Days to 76 Minutes
• DAGCN: Dual Attention Graph Convolutional Networks
• T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor
• Computational Imaging for VLBI Image Reconstruction (2016) ⭐
• AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning
• Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM Models
• ASAP: Architecture Search, Anneal and Prune
• Revisiting EmbodiedQA: A Simple Baseline and Beyond
• Accelerated Neural Networks on OpenCL Devices Using SYCL-DNN
• A Closer Look at Few-shot Classification
• Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
• Streamlined Dense Video Captioning
• Analysing Mathematical Reasoning Abilities of Neural Models
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
• Density Matching for Bilingual Word Embedding
• Characterizing the Social Interactions in the Artificial Bee Colony Algorithm
• MOTS: Multi-Object Tracking and Segmentation
• From Coarse to Fine: Robust Hierarchical Localization at Large Scale
• Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
• Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks
• Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model Agnostic Interpretations
• Feature Learning Viewpoint of AdaBoost and a New Algorithm
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation [code]
• A Selective Overview of Deep Learning
• Pun Generation with Surprise ⭐
• Unsupervised Recurrent Neural Network Grammars
• Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
• Tutorial: Safe and Reliable Machine Learning
• A Discussion on Solving Partial Differential Equations using Neural Networks
• Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving
• PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• Optimising Trotter-Suzuki Decompositions for Quantum Simulation Using Evolutionary Strategies
• A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms
• The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
• On the Performance of Differential Evolution for Hyperparameter Tuning
• GraphTSNE: A Visualization Technique for Graph-Structured Data
• Learning Not to Learn: Training Deep Neural Networks with Biased Data
• Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
• An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search
• Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation
• Precise Detection in Densely Packed Scenes
• Deep neural networks can predict mortality from 12-lead electrocardiogram voltage data
• Self-critical n-step Training for Image Captioning
• Pedestrian Detection in Thermal Images using Saliency Maps
• Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
• ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging
• Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces
• Fooling automated surveillance cameras: adversarial patches to attack person detection
• Unsupervised Part-Based Disentangling of Object Shape and Appearance
• Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances
• A General Neural Network Architecture for Persistence Diagrams and Graph Classification
• Mercator: uncovering faithful hyperbolic embeddings of complex networks
• Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach
• The Use of Unlabeled Data versus Labeled Data for Stopping Active Learning for Text Classification
• Variational approach to unsupervised learning
• A Novel Re-weighting Method for Connectionist Temporal Classification
• Language Models with Transformers
• LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
• Text Classification Algorithms: A Survey
• The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
• Neural Logic Reinforcement Learning
• Segmenting the Future
• Holistic Large Scale Video Understanding
• Understanding the Behaviors of BERT in Ranking
• Machine learning for long-distance quantum communication
• Attention Augmented Convolutional Networks
• Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors
• Differentiable Pruning Method for Neural Networks
• BERTScore: Evaluating Text Generation with BERT [code]
• Out of the Box: A combined approach for handling occlusion in Human Pose Estimation
• RepPoints: Point Set Representation for Object Detection
• Generated Loss, Augmented Training, and Multiscale VAE
• Latent Variable Algorithms for Multimodal Learning and Sensor Fusion
• Unsupervised Deep Learning by Neighbourhood Discovery
• Unsupervised Data Augmentation
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Dynamic Demand Prediction for Expanding Electric Vehicle Sharing Systems
• Aequitas: A Bias and Fairness Audit Toolkit
• Beyond Gradient Descent for Regularized Segmentation Losses
• A Review of Modularization Techniques in Artificial Neural Networks
• Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• DAC: The Double Actor-Critic Architecture for Learning Options
• Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage
• Adversarial Examples: Opportunities and Challenges
• Provable limitations of deep learning ⭐
• Evaluating Recurrent Neural Network Explanations
• Teaching AI, Ethics, Law and Policy
• Challenges and Pitfalls of Reproducing Machine Learning Artifacts
• Generating Artificial Data for Private Deep Learning
• Exploring Urban Air Quality with MAPS: Mobile Air Pollution Sensing
• Hierarchical Recurrent Neural Network for Video Summarization
• On Exact Computation with an Infinitely Wide Neural Net ⭐
• Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
• Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
• Wave Physics as an Analog Recurrent Neural Network
• TVQA+: Spatio-Temporal Grounding for Video Question Answering
• VideoBERT: A Joint Model for Video and Language Representation Learning

---

03/2019

• Predicting Research Trends From Arxiv
• Asynchronous Federated Optimization
• Improving Transparency of Deep Neural Inference Process
• GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks
• Unsupervised Discovery of Parts, Structure, and Dynamics
• Continual Learning via Neural Pruning
• Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Data
• Hyperdrive: A Multi-Chip Systolically Scalable Binary-Weight CNN Inference Engine
• High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors
• Survey of Text-based Epidemic Intelligence: A Computational Linguistic Perspective
• AutoML @ NeurIPS 2018 challenge: Design and Results
• MILDNet: A Lightweight Single Scaled Deep Ranking Architecture
• AI2-THOR: An Interactive 3D Environment for Visual AI
• VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning
• Natural Language Interaction with Explainable AI Models
• Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness
• Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
• Lipschitz Generative Adversarial Nets
• Scalable Facial Image Compression with Deep Feature Reconstruction
• AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming
• MirrorGAN: Learning Text-to-image Generation by Redescription
• A Deep Patent Landscaping Model using Transformer and Graph Convolutional Network
• MILDNet: A Lightweight Single Scaled Deep Ranking Architecture
• Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning
• Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2
• Cleaning tasks knowledge transfer between heterogeneous robots: a deep learning approach
• Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis [code]
• RVOS: End-to-End Recurrent Network for Video Object Segmentation [code]
• Improving Transparency of Deep Neural Inference Process
• Visual Semantic Information Pursuit: A Survey
• Assessing Generalization in Deep Reinforcement Learning
• On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models
• Policy Distillation and Value Matching in Multiagent Reinforcement Learning
• Selective Kernel Networks
• Neuromorphic Hardware learns to learn
• DeepHuman: 3D Human Reconstruction from a Single Image
• Benchmarking Natural Language Understanding Services for building Conversational Agents
• A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks
• BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
• Enabling Spike-based Backpropagation in State-of-the-art Deep Neural Network Architectures
• A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning
• ROS2Learn: a reinforcement learning framework for ROS 2
• Show, Translate and Tell
• Improving Neural Architecture Search Image Classifiers via Ensemble Learning
• Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition
• Autoregressive Models for Sequences of Graphs
• Human Activity Recognition for Edge Devices
• EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras
• Interpretable Deep Learning in Drug Discovery
• Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks
• Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation
• Neutron: An Implementation of the Transformer Translation Model and its Variants
• Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
• Beyond Turing: Intelligent Agents Centered on the User
• Deep Reinforcement Learning with Feedback-based Exploration
• Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Responses to a Critique of Artificial Moral Agents
• Inserting Videos into Videos
• Learning Correspondence from the Cycle-Consistency of Time
• Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
• CoCoNet: A Collaborative Convolutional Network
• A Principled Approach for Learning Task Similarity in Multitask Learning
• Memorable Maps: A Framework for Re-defining Places in Visual Place Recognition
• Learning to Caption Images through a Lifetime by Asking Questions
• Megapixel Photon-Counting Color Imaging using Quanta Image Sensor
• Recent advances in conversational NLP : Towards the standardization of Chatbot building
• Localization of Unmanned Aerial Vehicles in Corridor Environments using Deep Learning
• Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
• Dynamic Power Management for Neuromorphic Many-Core Systems
• Towards Characterizing Divergence in Deep Q-Learning
• Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
• LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
• A Graph-structured Dataset for Wikipedia Research
• Artificial Intelligence : from Research to Application ; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2019)
• Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
• Machine Learning for Data-Driven Movement Generation: a Review of the State of the Art
• A Methodology for Search Space Reduction in QoS Aware Semantic Web Service Composition
• Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
• Generative Models For Deep Learning with Very Scarce Data
• Progressive Sparse Local Attention for Video object detection
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
• In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
• IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules
• Deep Models for Relational Databases
• Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype
• Natural Language Generation at Scale: A Case Study for Open Domain Question Answering
• Actor and Action Video Segmentation from a Sentence ⭐
• DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction
• Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
• Towards a framework for the evolution of artificial general intelligence
• On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning
• Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
• Fine-tune BERT for Extractive Summarization
• Audio Caption: Listen and Tell
• MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
• HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
• Learning to Walk via Deep Reinforcement Learning
• Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
• Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems
• Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
• Continual Learning with Tiny Episodic Memories
• Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• NengoDL: Combining deep learning and neuromorphic modelling methods
• Autoregressive Policies for Continuous Control Deep Reinforcement Learning
• Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
• A Sober Look at Neural Network Initializations
• Using Monolingual Data in Neural Machine Translation: a Systematic Study
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods
• StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs
• GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
• nuScenes: A multimodal dataset for autonomous driving
• DetNAS: Neural Architecture Search on Object Detection
• Differentiable Scene Graphs
• BUT-FIT at SemEval-2019 Task 7: Determining the Rumour Stance with Pre-Trained Deep Bidirectional Transformers
• The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
• Random Language Model
• Extracting Success from IBM's 20-Qubit Machines Using Error-Aware Compilation
• Deep Radiomics for Brain Tumor Detection and Classification from Multi-Sequence MRI
• A Quantum Annealing-Based Approach to Extreme Clustering
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• TensorMask: A Foundation for Dense Object Segmentation
• 3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles
• Fast video object segmentation with Spatio-Temporal GANs
• Resilient Combination of Complementary CNN and RNN Features for Text Classification through Attention and Ensembling
• Deep learning for molecular generation and optimization - a review of the state of the art
• Needle in a Haystack: A Framework for Seeking Small Objects in Big Datasets

---

02/2019

• The Hanabi Challenge: A New Frontier for AI Research ⭐
• Towards Federated Learning at Scale: System Design
• Word Embeddings for Sentiment Analysis: A Comprehensive Empirical Survey
• The Natural Language of Actions
• AlphaStar: An Evolutionary Computation Perspective ⭐
• Declarative Data Analytics: a Survey
• CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning
• A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases
• Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era
• Solving The Exam Scheduling Problems in Central Exams With Genetic Algorithms
• Adaptive Gradient Refinement for Adversarial Perturbation Generation
• Computational Optimal Transport
• Parameter-Efficient Transfer Learning for NLP
• End-to-End Open-Domain Question Answering with BERTserini
• Discovering Implicational Knowledge in Wikidata
• Graph Classification with Recurrent Variational Neural Networks
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• FDDB-360: Face Detection in 360-degree Fisheye Images
• Reversible GANs for Memory-efficient Image-to-Image Translation
• Review Conversational Reading Comprehension
• Distilling Policy Distillation
• Virtual Training for a Real Application: Accurate Object-Robot Relative Localization without Calibration
• BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
• Beholder-GAN: Generation and Beautification of Facial Images with Conditioning on Their Beauty Level
• Optimized Compilation of Aggregated Instructions for Realistic Quantum Computers ⭐
• Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
• Understanding Chat Messages for Sticker Recommendation in Hike Messenger
• ML Health: Fitness Tracking for Production Models
• AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling
• Towards Federated Learning at Scale: System Design
• A Comprehensive Overview of Biometric Fusion
• Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning
• Software-Defined FPGA Accelerator Design for Mobile Deep Learning Applications
• Fourier Neural Networks: A Comparative Study
• Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target
• ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
• Task2Vec: Task Embedding for Meta-Learning
• Dropout is a special case of the stochastic delta rule: faster and more accurate deep learning
• Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
• TensorSCONE: A Secure TensorFlow Framework using Intel SGX
• Fast-SCNN: Fast Semantic Segmentation Network
• Peeking into the Future: Predicting Future Person Activities and Locations in Videos
• GET-AID: Visual Recognition of Human Rights Abuses via Global Emotional Traits
• Deep learning and face recognition: the state of the art
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• NAIL: A General Interactive Fiction Agent
• Toward Unsupervised Text Content Manipulation
• Quantum Entanglement in Deep Learning Architectures ⭐
• Image Processing in Quantum Computers
• ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning
• Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion
• Probabilistic Neural Architecture Search
• VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control
• Pseudo-extended Markov chain Monte Carlo
• Task2Vec: Task Embedding for Meta-Learning
• Deep Reinforcement Learning for Search, Recommendation, and Online Advertising: A Survey
• Multi-task learning to improve natural language understanding
• Deep Reinforcement Learning Based High-level Driving Behavior Decision-making Model in Heterogeneous Traffic
• AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices
• Crime Analysis using Open Source Information
• Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions
• WaveletFCNN: A Deep Time Series Classification Model for Wind Turbine Blade Icing Detection
• GeoGAN: A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images
• Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting
• Real-world Anomaly Detection in Surveillance Videos
• Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
• Transfer Learning for Sequence Labeling Using Source Model and Target Data
• Experimental Implementation of a Quantum Autoencoder via Quantum Adders
• Some Interesting Features of Memristor CNN ⭐
• Competitive Experience Replay
• Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond
• Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
• Contextual Word Representations: A Contextual Introduction
• Deep Learning for Image Super-resolution: A Survey
• Fast Efficient Hyperparameter Tuning for Policy Gradients
• Seven Myths in Machine Learning Research
• WIDER Face and Pedestrian Challenge 2018: Methods and Results
• Towards Explainable AI: Significance Tests for Neural Networks
• Investigating Generalisation in Continuous Deep Reinforcement Learning
• CrossNorm: Normalization for Off-Policy TD Reinforcement Learning
• Depthwise Convolution is All You Need for Learning Multiple Visual Domains
• CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
• Parenting: Safe Reinforcement Learning from Human Input
• Learned In Speech Recognition: Contextual Acoustic Word Embeddings
• Using Machine Learning to Guide Cognitive Modeling: A Case Study in Moral Reasoning
• Towards Hardware Implementation of Neural Network-based Communication Algorithms
• Language Models are Unsupervised Multitask Learners [code] ⭐
• SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
• Random Search and Reproducibility for Neural Architecture Search
• ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing
• Transfusion: Understanding Transfer Learning with Applications to Medical Imaging
• An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU
• Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)
• POINTCLEANNET: Learning to Denoise and Remove Outliers from Dense Point Clouds
• Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
• GSLAM: A General SLAM Framework and Benchmark
• The Devil is in the Decoder: Classification, Regression and GANs
• Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
• Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices
• Cloud-Based Autonomous Indoor Navigation: A Case Study
• Visualizing the Loss Landscape of Neural Nets
• Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
• Using Machine Learning to Guide Cognitive Modeling: A Case Study in Moral Reasoning
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• Perceptual Quality-preserving Black-Box Attack against Deep Learning Image Classifiers
• Innateness, AlphaZero, and Artificial Intelligence
• Universal Deep Neural Network Compression
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Deep Reinforcement Learning Based High-level Driving Behavior Decision-making Model in Heterogeneous Traffic
• Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer
• Multimodal Grounding for Sequence-to-Sequence Speech Recognition
• A Joint Deep Learning Approach for Automated Liver and Tumor Segmentation
• Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge
• Evaluating the Search Phase of Neural Architecture Search
• Topology of Learning in Artificial Neural Networks
• Evolutionary Neural AutoML for Deep Learning
• Simplifying Graph Convolutional Networks
• Adversarial Generation of Time-Frequency Features with application in audio synthesis
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling ⭐
• E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction
• Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment
• Comparison of Deep Neural Networks and Deep Hierarchical Models for Spatio-Temporal Data
• Distributionally Robust Reinforcement Learning
• The Multi-Lane Capsule Network (MLCN)
• Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks
• Pretraining-Based Natural Language Generation for Text Summarization
• GANSynth: Adversarial Neural Audio Synthesis
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Scalable Hyperbolic Recommender Systems
• Dual Attention Networks for Visual Reference Resolution in Visual Dialog
• Improving Robustness of Machine Translation with Synthetic Noise
• A Survey of Crowdsourcing in Medical Image Analysis
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
• DDFlow: Learning Optical Flow with Unlabeled Data Distillation
• Artificial Intelligence for Prosthetics - challenge solutions
• Banded Matrix Operators for Gaussian Markov Models in the Automatic Differentiation Era
• NAS-Bench-101: Towards Reproducible Neural Architecture Search
• Diagnosing Bottlenecks in Deep Q-learning Algorithms
• TraVeLGAN: Image-to-image Translation by Transformation Vector Learning
• Data augmentation using learned transforms for one-shot medical image segmentation
• Multi-Scale Quasi-RNN for Next Item Recommendation
• Efficient Learning for Deep Quantum Neural Networks
• Social Credibility Incorporating Semantic Analysis and Machine Learning: A Survey of the State-of-the-Art and Future Research Directions
• Adaptive Caching via Deep Reinforcement Learning
• TensorMap: Lidar-Based Topological Mapping and Localization via Tensor Decompositions
• Coloring Big Graphs with AlphaGoZero ⭐
• An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models ⭐
• The Termination Critic
• How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection
• Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
• DeepLO: Geometry-Aware Deep LiDAR Odometry
• Improving Missing Data Imputation with Deep Generative Models
• Accelerating Self-Play Learning in Go
• Reducing Artificial Neural Network Complexity: A Case Study on Exoplanet Detection
• Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU
• Attention is not Explanation
• Implicit Kernel Learning
• Architecting Dependable Learning-enabled Autonomous Systems: A Survey
• On Constrained Open-World Probabilistic Databases
• Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
• Learning to Generate Questions by Learning What not to Generate
• Domain-Constrained Advertising Keyword Generation
• Multilingual Neural Machine Translation with Knowledge Distillation
• StyleRemix: An Interpretable Representation for Neural Image Style Transfer
• Provable Guarantees for Gradient-Based Meta-Learning
• Deep Adversarial Network Alignment
• Multi-task hypernetworks
• Atomistic structure learning

---

01/2019

• Theory of Minds: Understanding Behavior in Groups Through Inverse Planning
• A Comprehensive Survey on Graph Neural Networks
• Face Recognition: A Novel Multi-Level Taxonomy based Survey
• DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation [code]
• Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning
• Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals
• A Critical Investigation of Deep Reinforcement Learning for Navigation
• Adversarial Examples versus Cloud-based Detectors: A Black-box Empirical Study
• Sheaves: A Topological Approach to Big Data
• AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection
• Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
• Text2Scene: Generating Compositional Scenes from Textual Descriptions
• Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
• Designing for Democratization: Introducing Novices to Artificial Intelligence Via Maker Kits
• Elimination of All Bad Local Minima in Deep Learning
• Location-Centered House Price Prediction: A Multi-Task Learning Approach
• Credit Assignment Techniques in Stochastic Computation Graphs
• Human Pose Estimation with Spatial Contextual Information
• Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination
• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
• Quaternion Recurrent Neural Networks
• Ten ways to fool the masses with machine learning
• Unrepresentative video data: A review and evaluation
• Automated Pruning for Deep Neural Network Compression
• Learning Combinations of Activation Functions
• Bandwidth Reduction using Importance Weighted Pruning on Ring AllReduce
• Exploring applications of deep reinforcement learning for real-world autonomous driving systems ⭐
• RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
• Gauges, Loops, and Polynomials for Partition Functions of Graphical Models
• Channel Locality Block: A Variant of Squeeze-and-Excitation
• What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning
• Transferable Adversarial Attacks for Image and Video Object Detection
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data
• Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
• The ISTI Rapid Response on Exploring Cloud Computing 2018
• FIGR: Few-shot Image Generation with Reptile
• Multi-stream CNN based Video Semantic Segmentation for Automated Driving
• Multi-style Generative Reading Comprehension
• GILT: Generating Images from Long Text
• On the Capabilities and Limitations of Reasoning for Natural Language Understanding
• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
• Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera
• Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support Systems
• The Lingering of Gradients: How to Reuse Gradients over Time
• Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks
• Asteroids Detection Technique: Classic "Blink" An Automated Approch
• Machine learning topological phases in real space
• Dirichlet Variational Autoencoder
• Recurrent Control Nets for Deep Reinforcement Learning
• Spherical CNNs on Unstructured Grids
• Risk-Aware Active Inverse Reinforcement Learning
• Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks
• An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Revealing interpretable object representations from human behavior
• Deep Learning for Human Affect Recognition: Insights and New Developments
• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context [code]
• Exploring Weight Symmetry in Deep Neural Networks
• Variable Importance Clouds: A Way to Explore Variable Importance for the Set of Good Models
• Motion Perception in Reinforcement Learning with Dynamic Objects
• Brief Review of Computational Intelligence Algorithms ⭐
• PVSS: A Progressive Vehicle Search System for Video Surveillance Networks
• Learning Face Age Progression: A Pyramid Architecture of GANs
• Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications
• PFML-based Semantic BCI Agent for Game of Go Learning and Prediction
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Accelerated Flow for Probability distributions
• On Finding Gray Pixels
• RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
• Motion Perception in Reinforcement Learning with Dynamic Objects
• Deep Learning for Anomaly Detection: A Survey
• An investigation of model-free planning
• Dialog System Technology Challenge 7
• On Event Causality Detection in Tweets
• A Biologically Inspired Visual Working Memory for Deep Networks
• Agent-Agnostic Human-in-the-Loop Reinforcement Learning ⭐
• Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes
• Using Scene Graph Context to Improve Image Generation
• Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving
• Summarization and Visualization of Large Volumes of Broadcast Video Data
• Trace-back Along Capsules and Its Application on Semantic Segmentation
• LiFF: Light Field Features in Scale and Depth
• Human few-shot learning of compositional instructions
• Self-Supervised Deep Active Accelerated MRI
• Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition
• Toward Explainable Fashion Recommendation
• A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection
• DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
• Transfer Learning for Prosthetics Using Imitation Learning
• Approaching Ethical Guidelines for Data Scientists
• Identifying and Correcting Label Bias in Machine Learning
• Low Precision Constant Parameter CNN on FPGA
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
• Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
• Fair and Unbiased Algorithmic Decision Making: Current State and Future Challenges
• AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning
• The Limitations of Adversarial Training and the Blind-Spot Attack
• ALiPy: Active Learning in Python
• Hybrid Recommender Systems: A Systematic Literature Review
• Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
• Recombination of Artificial Neural Networks
• Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• A deep learning approach to solar-irradiance forecasting in sky-videos
• Interpretable machine learning: definitions, methods, and applications
• Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation
• TensorFlow.js: Machine Learning for the Web and Beyond
• Attentive Neural Processes ⭐
• Convolutional Neural Networks combined with Runge-Kutta Methods
• Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
• Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails
• VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control
• AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving
• Artificial Neural Networks
• Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
• Assessing BERT's Syntactic Abilities
• EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
• UltraCompression: Framework for High Density Compression of Ultrasound Volumes using Physics Modeling Deep Neural Networks
• Primitive-based 3D Building Modeling, Sensor Simulation, and Estimation
• The Oracle of DLphi
• Recent Advances in Autoencoder-Based Representation Learning
• Towards Building the Semantic Map from a Monocular Camera with a Multi-task Network
• DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
• Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing
• Ensemble Feature for Person Re-Identification
• Machine Learning Techniques for Brand-Influencer Matchmaking on the Instagram Social Network
• Predicting Variable Types in Dynamically Typed Programming Languages
• Light-Field for RF
• Passage Re-ranking with BERT
• Learning to Design Circuits
• Video-Based Pedestrian Attribute Recognition
• Genetic Algorithms and the Traveling Salesman Problem a historical Review
• Evolving embodied intelligence from materials to machines
• CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs
• Survey of Bayesian Networks Applications on Unmanned Intelligent Autonomous Vehicles
• Deep learning-based electroencephalography analysis: a systematic review
• Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents
• Optimization Models for Machine Learning: A Survey
• Solar-Sail Trajectory Design of Multiple Near Earth Asteroids Exploration Based on Deep Neural Network
• Block Argumentation
• Natively Interpretable Machine Learning and Artificial Intelligence: Preliminary Results and Future Directions
• NeuNetS: An Automated Synthesis Engine for Neural Network Design
• WALL-E: An Efficient Reinforcement Learning Research Framework
• Learning Dexterous In-Hand Manipulation
• Training Neural Networks with Local Error Signals
• Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning
• cross-lingual Language Model Pretraining
• DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features
• Improved Selective Refinement Network for Face Detection
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• Design of Real-time Semantic Segmentation Decoder for Automated Driving
• Causal Reasoning from Meta-reinforcement Learning
• Automated Essay Scoring based on Two-Stage Learning
• Decoupled Greedy Learning of CNNs
• Open-ended Learning in Symmetric Zero-sum Games
• Learning Neurosymbolic Generative Models via Program Synthesis
• Emotion Detection and Analysis on Social Media
• Large-Batch Training for LSTM and Beyond
• Theoretically Principled Trade-off between Robustness and Accuracy
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• QGAN: Quantized Generative Adversarial Networks
• Explainable Failure Predictions with RNN Classifiers based on Time Series Data
• Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Learning Neurosymbolic Generative Models via Program Synthesis
• Three principles of data science: predictability, computability, and stability (PCS)
• Understanding Geometry of Encoder-Decoder CNNs
• PuppetGAN: Transferring Disentangled Properties from Synthetic to Real Images
• Finding Archetypal Spaces for Data Using Neural Networks
• Generating Textual Adversarial Examples for Deep Learning Models: A Survey
• Using Pre-Training Can Improve Model Robustness and Uncertainty
• Non-computability of human intelligence
• Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification
• DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks
• Hierarchically Clustered Representation Learning
• Close to Human Quality TTS with Transforme
• Lyapunov-based Safe Policy Optimization for Continuous Control
• A deep learning framework for assessment of quality of rehabilitation exercises
• Limitations of Assessing Active Learning Performance at Runtime
• Evaluating Word Embedding Models: Methods and Experimental Results
• Cloud-Net: An end-to-end Cloud Detection Algorithm for Landsat 8 Imagery
• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• Generalized Label Propagation Methods for Semi-Supervised Learning
• Pay Less Attention with Lightweight and Dynamic Convolutions
• FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
• Guiding Policies with Language via Meta-Learning
• A BERT Baseline for the Natural Questions
• MultiLock: Mobile Active Authentication based on Multiple Biometric and Behavioral Patterns
• Fair Regression for Health Care Spending
• Revisiting Self-Supervised Visual Representation Learning
• The Value Function Polytope in Reinforcement Learning
• A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
• Go-Explore: a New Approach for Hard-Exploration Problems
• DDSL: Deep Differentiable Simplex Layer for Learning Geometric Signals
• The Evolved Transformer
• HyperGAN: A Generative Model for Diverse, Performant Neural Networks
• Twitter Job/Employment Corpus: A Dataset of Job-Related Discourse Built with Humans in the Loop
• Learning and Evaluating General Linguistic Intelligence
• The Value Function Polytope in Reinforcement Learning
• Multi-Task Deep Neural Networks for Natural Language Understanding
• Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
• The Second Conversational Intelligence Challenge (ConvAI2)
• Probabilistic Discriminative Learning with Layered Graphical Models
• Towards Machine-assisted Meta-Studies: The Hubble Constant
• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Going
• Combating Fake News: A Survey on Identification and Mitigation Techniques
• Go-Explore: a New Approach for Hard-Exploration Problems
• A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning
• Deep Learning for Video Game Playing
• Deep Discriminative Representation Learning with Attention Map for Scene Classification
• Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
• Fixup Initialization: Residual Learning Without Normalization ⭐
• Predictive Maintenance in Photovoltaic Plants with a Big Data Approach

---

12/2018

• Theory of Cognitive Relativity: A Promising Paradigm for True AI
• Modeling Theory of Mind for Autonomous Agents with Probabilistic Programs
• Bag of Tricks for Image Classification with Convolutional Neural Networks
• Learning 3D Human Dynamics from Video
• MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language
• Designing quantum experiments with a genetic algorithm
• SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
• Brief survey of Mobility Analyses based on Mobile Phone Datasets
• Wireless Data Acquisition for Edge Learning: Importance Aware Retransmission
• An Introduction to Deep Reinforcement Learning
• Visual Object Networks: Image Generation with Disentangled 3D Representation
• Project Rosetta: A Childhood Social, Emotional, and Behavioral Developmental Ontology
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• Online Model Distillation for Efficient Video Inference
• Adversarial Vision Challenge
• Recursive Visual Attention in Visual Dialog
• Deep Architectures for Learning Context-dependent Ranking Functions
• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• e-SNLI: Natural Language Inference with Natural Language Explanations
• Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs
• Tube-CNN: Modeling temporal evolution of appearance for object detection in video
• Computer Vision for Autonomous Vehicles
• A Parallel Divide-and-Conquer based Evolutionary Algorithm for Large-scale Optimization
• Sim-to-Real Optimization of Complex Real World Mobile Network with Imperfect Information via Deep Reinforcement Learning from Self-play
• Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
• HAQ: Hardware-Aware Automated Quantization
• Meta-Transfer Learning for Few-Shot Learning
• Security and Privacy Issues in Deep Learning
• DNQ: Dynamic Network Quantization
• Summarizing Videos with Attention
• Exploring galaxy evolution with generative models
• EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search
• Visual Attention for Behavioral Cloning in Autonomous Driving
• Law and Adversarial Machine Learning
• A Style-Based Generator Architecture for Generative Adversarial Network
• Improving fairness in machine learning systems: What do industry practitioners need?
• Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation
• IRLAS: Inverse Reinforcement Learning for Architecture Search
• Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems
• Adversarial Transfer Learning
• Neural Approaches to Conversational AI
• Revisiting Exploration-Conscious Reinforcement Learning
• Deep Face Image Retrieval: a Comparative Study with Dictionary Learning
• TextBugger: Generating Adversarial Text Against Real-world Applications
• A comparison of cluster algorithms as applied to unsupervised surveys
• On-line Adaptative Curriculum Learning for GANs
• Transfer Learning using Representation Learning in Massive Online Open Courses
• DeepProbLog: Neural Probabilistic Logic Programming
• Linking Artificial Intelligence Principles
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
• Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation
• Comixify: Transform video into a comics
• Policy Search in Continuous Action Domains: an Overview
• Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders
• Bayesian Optimization in AlphaGo
• A Tutorial on Deep Latent Variable Models of Natural Language
• Traceability of Deep Neural Networks
• TechKG: A Large-Scale Chinese Technology-Oriented Knowledge Graph
• Towards Real-Time Accurate Object Detection in Both Images and Videos Based on Dual Refinement
• The Entropy of Artificial Intelligence and a Case Study of AlphaZero from Shannon's Perspective
• Contingency-Aware Exploration in Reinforcement Learning
• Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
• Latent Dirichlet Allocation in Generative Adversarial Networks
• Quantum Memristors in Quantum Photonics
• A Tutorial on Distance Metric Learning: Mathematical Foundations, Algorithms and Software
• Evolutionary Neural Architecture Search for Image Restoration
• DVC: An End-to-end Deep Video Compression Framework
• Soft Actor-Critic Algorithms and Applications
• Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera
• End to End Video Segmentation for Driving : Lane Detection For Autonomous Car
• Deep Learning on Graphs: A Survey
• Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures
• Scaling shared model governance via model splitting
• FML: Face Model Learning from Videos
• Generative One-Shot Learning (GOL): A Semi-Parametric Approach to One-Shot Learning in Autonomous Vision
• Machine Learning in Cyber-Security - Problems, Challenges and Data Sets
• Deep Paper Gestalt
• Deep Learning for Classical Japanese Literature
• Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks
• Progressive Data Science: Potential and Challenges
• A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series
• Molecular Dynamics with Neural-Network Potentials
• Graph Neural Networks: A Review of Methods and Applications
• wav2letter++: The Fastest Open-source Speech Recognition System
• A Survey of Hierarchy Identification in Social Networks
• nocaps: novel object captioning at scale
• Optimization Methods for Large-Scale Machine Learning
• Deep Graph Infomax
• Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems
• The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
• GamePad: A Learning Environment for Theorem Proving
• Lenia - Biology of Artificial Life
• Generalisation in humans and deep neural networks
• Learning from Web Data: the Benefit of Unsupervised Object Localization
• Learning to Navigate the Web
• Sample Efficient Adaptive Text-to-Speech
• A Gentle Introduction to Deep Learning in Medical Image Processing
• ProMP: Proximal Meta-Policy Search
• A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
• Face Hallucination Revisited: An Exploratory Study on Dataset Bias
• Lifelong Testing of Smart Autonomous Systems by Shepherding a Swarm of Watchdog Artificial Intelligence Agents
• Analysis Methods in Neural Language Processing: A Survey
• Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications
• Dialog-based Interactive Image Retrieval
• Quantifying Generalization in Reinforcement Learning
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• Tiramisu: A Polyhedral Compiler for Expressing Fast and Portable Code
• Generalization Error in Deep Learning
• Photo Wake-Up: 3D Character Animation from a Single Photo
• Data-Efficient Hierarchical Reinforcement Learning
• A General Approach to Domain Adaptation with Applications in Astronomy
• A Survey on Deep Learning for Named Entity Recognition
• Parallelized Interactive Machine Learning on Autonomous Vehicles
• Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness
• Training Deep Capsule Networks ⭐
• Deep Learning for Inferring the Surface Solar Irradiance from Sky Imagery
• Learning Not to Learn: Training Deep Neural Networks with Biased Data
• RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
• GaussianProcesses.jl: A Nonparametric Bayes package for the Julia Language
• Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
• Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
• Structure Learning of Sparse GGMs over Multiple Access Networks
• Large Multistream Data Analytics for Monitoring and Diagnostics in Manufacturing Systems
• ECG Segmentation by Neural Networks: Errors and Correction
• A Review on The Use of Deep Learning in Android Malware Detection
• Informative Object Annotations: Tell Me Something I Don't Know
• A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition
• Reward Constrained Policy Optimization
• Perceptrons from Memristors
• How Powerful are Graph Neural Networks?
• Optimizing Market Making using Multi-Agent Reinforcement Learning
• End-to-End Latent Fingerprint Search
• When Does Stochastic Gradient Algorithm Work Well?
• General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms
• Portfolio Optimization for Cointelated Pairs: SDEs vs. Machine Learning
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications ⭐
• Fingerprint Presentation Attack Detection: Generalization and Efficiency
• Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
• SLIM LSTMs
• Partially Non-Recurrent Controllers for Memory-Augmented Neural Networks
• ATHENA: Automated Tuning of Genomic Error Correction Algorithms using Language Models
• Deep Residual Learning in the JPEG Transform Domain
• A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations
• ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers
• Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach
• Improving fairness in machine learning systems: What do industry practitioners need?
• Meta Reinforcement Learning with Distribution of Exploration Parameters Learned by Evolution Strategies
• Greedy Layerwise Learning Can Scale to ImageNet
• CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras
• Learn to Interpret Atari Agents
• BNN+: Improved Binary Network Training
• AIR5: Five Pillars of Artificial Intelligence Research
• Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
• CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences
• ORIGAMI: A Heterogeneous Split Architecture for In-Memory Acceleration of Learning
• Learning to Design RNA
• Safety and Trustworthiness of Deep Neural Networks: A Survey ⭐
• Deep Learning on Graphs: A Survey
• Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks
• Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3

---

11/2018

• Horizon: Facebook's Open Source Applied Reinforcement Learning Platform [code]
• Applications of Deep Learning to Nuclear Fusion Research
• Towards Explainable NLP: A Generative Explanation Framework for Text Classification
• CariGANs: Unpaired Photo-to-Caricature Translation
• Predicting Demographics, Moral Foundations, and Human Values from Digital Behaviors
• Algorithms for screening of Cervical Cancer: A chronological review
• A Survey on Natural Language Processing for Fake News Detection
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• A Fast Algorithm for Clustering of High Dimensional Feature Vectors
• Toward an AI Physicist for Unsupervised Learning
• You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
• Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks
• Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
• Language GANs Falling Short
• Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
• Learning from Demonstration in the Wild
• A Survey on Data Collection for Machine Learning: a Big Data - AI Integration Perspective
• Mesh-TensorFlow: Deep Learning for Supercomputers
• ImageNet/ResNet-50 Training in 224 Seconds
• Natural Environment Benchmarks for Reinforcement Learning
• Reward learning from human preferences and demonstrations in Atari ⭐
• Mathematical Analysis of Adversarial Attacks
• Going Deeper with Semantics: Video Activity Interpretation using Semantic Contextualization
• Towards Explainable Deep Learning for Credit Lending: A Case Study
• Preliminary Studies on a Large Face Database
• Effect of data reduction on sequence-to-sequence neural TTS
• Effects of Dataset properties on the training of GANs
• On-line Adaptative Curriculum Learning for GANs
• GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
• Active Inverse Reward Design
• DropFilter: A Novel Regularization Method for Learning Convolutional Neural Networks
• Incentivizing the Dynamic Workforce: Learning Contracts in the Gig-Economy
• ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion
• An Algorithmic Perspective on Imitation Learning
• DeRPN: Taking a further step toward more general object detection
• Activation Maximization Generative Adversarial Nets
• CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
• Streaming End-to-end Speech Recognition For Mobile Devices
• Economics of Human-AI Ecosystem: Value Bias and Lost Utility in Multi-Dimensional Gaps
• Scalable agent alignment via reward modeling: a research direction ⭐
• Automatic Paper Summary Generation from Visual and Textual Information
• Learned Video Compression
• PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable Convolution
• Image Classification at Supercomputer Scale
• The PyTorch-Kaldi Speech Recognition Toolkit
• Adversarial Autoencoders for Generating 3D Point Clouds
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• An Introduction to Image Synthesis with Generative Adversarial Nets
• When Conventional machine learning meets neuromorphic engineering: Deep Temporal Networks (DTNets) a machine learning frawmework allowing to operate on Events and Frames and implantable on Tensor Flow Like Hardware
• Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
• On Human Robot Interaction using Multiple Modes
• Guiding Policies with Language via Meta-Learning
• Improving Automatic Source Code Summarization via Deep Reinforcement Learning
• Pitfalls of Graph Neural Network Evaluation
• Emergence of linguistic conventions in multi-agent reinforcement learning
• The Mirage of Action-Dependent Baselines in Reinforcement Learning
• Automated Algorithm Selection on Continuous Black-Box Problems By Combining Exploratory Landscape Analysis and Machine Learning
• The Mafiascum Dataset: A Large Text Corpus for Deception Detection
• Deeper Interpretability of Deep Networks
• High Speed Event-based Face Detection and Tracking in the Blink of an Eye
• Explicit Bias Discovery in Visual Question Answering Models
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Towards Global Explanations for Credit Risk Scoring
• Watermark Retrieval from 3D Printed Objects via Convolutional Neural Networks
• Deep Active Learning with a Neural Architecture Search
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• HAQ: Hardware-Aware Automated Quantization
• Artificial Intelligence-Defined 5G Radio Access Networks
• Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs
• 50 Years of Test (Un)fairness: Lessons for Machine Learning
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Gradient Descent Finds Global Minima of Deep Neural Networks
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Context-Aware Crowd Counting
• InstaNAS: Instance-aware Neural Architecture Search
• Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
• Machine Learning for Health (ML4H) Workshop at NeurIPS 2018
• Representation Mixing for TTS Synthesis
• Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
• Robust Artificial Intelligence and Robust Human Organizations ⭐
• Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
• MLModelScope: Evaluate and Measure ML Models within AI Pipelines
• From Recognition to Cognition: Visual Commonsense Reasoning
• Interpretable Convolutional Filters with SincNet
• Dataset Distillation
• LSTA: Long Short-Term Attention for Egocentric Action Recognition
• Feature-Fused SSD: Fast Detection for Small Objects
• Deformable ConvNets v2: More Deformable, Better Results
• TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
• A computational perspective of the role of Thalamus in cognition
• Towards Long-Term Memory for Social Robots: Proposing a New Challenge for the RoboCup@Home League
• Automated Algorithm Selection: Survey and Perspectives
• LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild
• Towards Decentralization of Social Media
• Neuro-memristive Circuits for Edge Computing: A review
• Deep Reinforcement Learning for Autonomous Driving
• Actor-Critic Policy Optimization in Partially Observable Multiagent Environments
• Prioritizing Starting States for Reinforcement Learning
• DLHub: Model and Data Serving for Science
• Towards Identifying and Managing Sources of Uncertainty in AI and Machine Learning Models - An Overview
• Kalman filter demystified: from intuition to probabilistic graphical model to real case in financial markets
• Snap ML: A Hierarchical Framework for Machine Learning
• Face Detection in the Operating Room: Comparison of State-of-the-art Methods and a Self-supervised Approach
• Demonstrating Advantages of Neuromorphic Computation: A Pilot Study
• ShelfNet for Real-time Semantic Segmentation
• Attentive Relational Networks for Mapping Images to Scene Graphs
• ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
• Recurrent Relational Networks
• Fashion-Gen: The Generative Fashion Dataset and Challenge
• A Century Long Commitment to Assessing Artificial Intelligence and its Impact on Society
• Foot Pressure from Video: A Deep Learning Approach to Predict Dynamics from Kinematics
• Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
• Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

---

10/2018

• The Profiling Machine: Active Generalization over Knowledge
• AI Benchmark: Running Deep Neural Networks on Android Smartphones
• A deep learning pipeline for product recognition on store shelves
• MyCaffe: A Complete C# Re-Write of Caffe with Reinforcement Learning
• Quantum Artificial Life in an IBM Quantum Computer
• Finding Solutions to Generative Adversarial Privacy
• Towards Fast and Energy-Efficient Binarized Neural Network Inference on FPGA
• Scaling Video Analytics Systems to Large Camera Deployments
• From Soft Classifiers to Hard Decisions: How fair can we be?
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• Comparison of Reinforcement Learning algorithms applied to the Cart Pole problem
• Auto-Keras: Efficient Neural Architecture Search with Network Morphism
• An Overview on Application of Machine Learning Techniques in Optical Networks
• A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
• Transfer Metric Learning: Algorithms, Applications and Outlooks
• Secure Deep Learning Engineering: A Software Quality Assurance Perspective
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [code] [code] ⭐
• Is multiagent deep reinforcement learning the answer or the question? A brief survey
• CURIOUS: Intrinsically Motivated Multi-Task, Multi-Goal Reinforcement Learning
• On the Margin Theory of Feedforward Neural Networks
• Private Machine Learning in TensorFlow using Secure Computation
• Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
• Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUs
• Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
• Do Deep Generative Models Know What They Don't Know?
• Neighbourhood Consensus Networks
• The Uncertainty Bellman Equation and Exploration
• Humans are still the best lossy image compressors
• Model-Based Active Exploration
• Reversible Recurrent Neural Networks
• Graph Convolutional Reinforcement Learning for Multi-Agent Cooperation
• Multi-Agent Common Knowledge Reinforcement Learning
• Tackling Sequence to Sequence Mapping Problems with Neural Networks
• Applying Deep Learning To Airbnb Search
• Inverse reinforcement learning for video games
• Fast and accurate object detection in high resolution 4K and 8K video using GPUs
• Towards Efficient Large-Scale Graph Neural Network Computing
• An Exploration of Dropout with RNNs for Natural Language Inference
• Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
• Memory Replay GANs: learning to generate images from new categories without forgetting
• You May Not Need Attention [code]
• Face Recognition: From Traditional to Deep Learning Methods
• Democratizing Production-Scale Distributed Deep Learning
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
• WaveGlow: A Flow-based Generative Network for Speech Synthesis
• Dial2Desc: End-to-end Dialogue Description Generation
• Taking Human out of Learning Applications: A Survey on Automated Machine Learning
• DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution

---

09/2018

• Hamiltonian Descent Methods
• Deep Learning for Generic Object Detection: A Survey
• Unity: A General Platform for Intelligent Agents
• Five lessons from building a deep neural network recommender for marketplaces
• Focus Group on Artificial Intelligence for Health
• Deep Learning in Information Security
• LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts
• IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
• Identifying Real Estate Opportunities using Machine Learning
• Deep Learning Towards Mobile Applications
• HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments
• Urban morphology meets deep learning: Exploring urban forms in one million cities, town and villages across the planet
• Graph Convolutional Networks for Text Classification
• Identifying Generalization Properties in Neural Networks
• Towards Deep and Representation Learning for Talent Search at LinkedIn
• Cellular automata as convolutional neural networks
• Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
• AlphaSeq: Sequence Discovery with Deep Reinforcement Learning
• Learning to Interpret Satellite Images Using Wikipedia
• Visual Analytics for Automated Model Discovery
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Stakeholders in Explainable AI
• Adversarial Attacks and Defences: A Survey
• Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture
• Deep Learning in Mobile and Wireless Networking: A Survey
• Hierarchical Deep Multiagent Reinforcement Learning
• Massively Parallel Hyperparameter Tuning

---

08/2018

• Backprop Evolution
• Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation
• Large Scale Language Modeling: Converging on 40GB of Text in Four Hours. paper
• RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising
• Neural Arithmetic Logic Units
• CornerNet: Detecting Objects as Paired Keypoints
• A Survey on Deep Transfer Learning
• YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud
• Dialog-context aware end-to-end speech recognition
• An Efficient Deep Reinforcement Learning Model for Urban Traffic Control
• Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis
• GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware
• Application of End-to-End Deep Learning in Wireless Communications Systems
• A Short Note about Kinetics-600
• Smart City Development with Urban Transfer Learning
• Deep Learning Advances on Different 3D Data Representations: A Survey
• Skill Rating for Generative Models. paper
• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network. paper
• Hierarchical Attention: What Really Counts in Various NLP Tasks . paper
• Neural Architecture Search: A Survey. paper
• Rapid Adaptation of Neural Machine Translation to New Languages. paper
• A Survey on Sentiment and Emotion Analysis for Computational Literary Studies. paper
• Video-to-Video Synthesis. arxiv [code]
• CoQA: A Conversational Question Answering Challenge. arxiv
• QuAC : Question Answering in Context. arxiv
• Everybody Dance Now. paper
• Contextual Parameter Generation for Universal Neural Machine Translation. paper
• Fusion++: Volumetric Object-Level SLAM. paper
• Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs
• FPGA Implementation of Convolutional Neural Networks with Fixed-Point Calculations
• Generalisation in humans and deep neural networks
• All You Need is "Love": Evading Hate-speech Detection

---

07/2018

• Troubling Trends in Machine Learning Scholarship
• Machine Learning in High Energy Physics Community White Paper
• Quasi-Dilemmas for Artificial Moral Agents
• Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
• Comparing Dynamics: Deep Neural Networks versus Glassy Systems
• Financial Trading as a Game: A Deep Reinforcement Learning Approach
• Natural Language Processing for Information Extraction
• Video Summarisation by Classification with Deep Reinforcement Learning
• Generative models on accelerated neuromorphic hardware
• A Survey of Knowledge Representation and Retrieval for Learning in Service Robotics
• Zipf's law in 50 languages: its structural pattern, linguistic interpretation, and cognitive motivation
• JUMPER: Learning When to Make Classification Decisions in Reading
• Universal Word Segmentation: Implementation and Interpretation
• End-to-End Race Driving with Deep Reinforcement Learning
• Taskonomy: Disentangling Task Transfer Learning
• ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech. arxiv
• Hierarchical Multi Task Learning With CTC. arxiv
• When deep learning meets security. arxiv
• Object Detection with Deep Learning: A Review. arxiv
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search. arxiv
• Implementing Neural Turing Machines
• Talk the Walk: Navigating New York City through Grounded Dialogue
• The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks
• Learning by Asking Questions
• Deep learning in agriculture: A survey
• Learning Plannable Representations with Causal InfoGAN, ICML / IJCAI / AAMAS 2018 Workshop on(PAL-18).
• Progressive Neural Architecture Search
• Variational Bayesian Reinforcement Learning with Regret Bounds
• Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes
• Learning from Delayed Outcomes with Intermediate Observations
• A Survey of the Usages of Deep Learning in Natural Language Processing
• The GAN Landscape: Losses, Architectures, Regularization, and Normalization
• Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
• TherML: Thermodynamics of Machine Learning
• Neural Processes
• GAN Q-learning
• LaneNet: Real-Time Lane Detection Networks for Autonomous Driving
• TextWorld: A Learning Environment for Text-based Games, ICML/IJCAI 2018.
• Perceptrons from Memristors
• Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
• Large-Scale Visual Speech Recognition

---

---

|| dl-research-groups | dl-frameworks | dl1+dl2 | awesome-dl+roadmap+ml | CB-Insights_AI-100 + AI100_2 | ai-angelList | machine-learning-surveys |graph-based-deep-learning-literature||

|| a--rnn | a-deep-vision | a--random-forest | a-computer-vision | a-deep-learning | a-p | d-l-p | drlp | DeepLearningImplementations | drlp2 | dl-papernotes | dl-r | med-appl | very-dl | nn.papers | a-GAN | rl.papers| dnn.med | cuda.programming | caltech.cuda | rtb-papers | deep-learning-nlp-rl-papers | nips2017 | deep_learning_object_detection | MLiterature ||

|| Outline of artificial intelligence | Outline of machine learning | Outline of computer vision | Outline of natural language processing | Outline of robotics | List of datasets for machine learning research| ai applications | UCI.ML.DATASETS | public.datasets | kaggle.datasets | datasets.gh.list | Origin_of_speech ||

|| awesome-nlp | nlp_tasks | DeepNLP-models-Pytorch | oxford.nlp.lectures | stanford.nlp.lectures | nltk.org/book | DL4NLP | cs388.utexas.nlp | nlp-datasets | DL-NLP-Readings | gt-nlp-class| GNNPapers ||

[Deep Learning Resources], [DL_libraries_final_Rankings]

---

ML/DL Publications

• Arxiv Sanity Preserver
• NIPS
• ICML-17
• AAAI
• CVPapers
• arxiv.ml
• arxiv.cvpr
• arxiv.ai
• arxiv.ne
• arxiv.ro
• arxiv.nc
• hinton
• MILA
• FAIR
• deepmind
• brain team
• andrewng
• yann.lecun,nyu
• manning
• hiit.neuro
• grey.colorado.edu.CCNL
• dbsystem
• nvidia.ml.research
• stanford.vision.lab
• BAIR.people + courses
• CSAIL.people + publications
• SAIL.people + courses
• google.machineIntelligence
• google.MachinePerception
• google.MachineTranslation
• google.NaturalLanguageProcessing
• google.AIResidency
• scholar.cvpr
• scholar.ai
• scholar.gt
• scholar.ro
• shoham
• ai.people
• ml.people
• AAAI.fellows
• UTA.ai
• UTA.dml
• wildml
• rl.gh.p
• nn.gh.p
• openai.requests.research
• psy.ox.ac.uk
• cs.ox.ac.uk
• CV.people
• arXivTimes

---

ML/DL Implementations

• deepmind.gh.code
• openai.gh.code
• facebookresearch.gh.code
• frameworks.dl
• ml.python
• deep.nlp.models.pytorch
• rl
• dl.keras.tf
• pytorch.list
• ml.algorithms
• cnn.benchmarks
• pytorch.tut
• pytorch.ex
• torch.start
• dl.tool
• rl.tf
• DCGAN.tf
• ntm.tf
• neural.style
• torch.rnn
• stanford.dl.ex
• deepq.tf
• gan
• ml.hackers.code.r
• bayesian.code.jn
• nn.dl.code
• nn.java
• ml.go
• numenta.gh.code
• tensorflow.gh.code
• neural.doodle.code
• ml.sf.engineering
• tf.models
• DL4NLP
• neural.style.torch
• opencog
• ml.jn.scikit
• bayesian.PyMC3
• tf.ex
• ALE
• aima.py
• deeplearning4j.code
• tflearn.tf
• resnet
• stanford.tf
• top.dl
• tensorlayer.dl.rl
• dl.keras
• dl.docker
• dl.list
• mila.gh.code
• microsoft.gh.code
• CSAILVision.gh.code
• NVIDIA.gh.code
• OpenNMT.code
• Tencent.code
• baidu.code
• stanfordnlp.code
• sar.ml
• sony.code
• ml
• PrincetonVision.code
• commaai.code
• NervanaSystems.code
• pytorch.code
• torch.code
• automl.code
• chainer.code
• dmlc.code
• BVLC.code
• caffe2.code
• aimacode.code
• opencog.code
• opencv.code
• oxford.deepnlp
• USC.ds.code
• gensim.nlp.ir
• scikit.learn.code
• tesseract.code
• ds.ipython
• ml.book
• ccs.video.cources
• eff.tf
• ml.tut
• swift.ai
• tf.book
• ml.mindmaps
• dl
• h2o.ai
• fast.ai
• tf.tut
• tf.tut
• PipelineAI
• PRML
• mlpack
• mit.nlp
• scikit.learn.contrib
• mit.ml.pdf
• ml.py.book
• onnx.code
• aml.sf
• dmml.sf
• prolog.ai
• deep.rl.1
• deep.rl.pytorch
• dl.tut
• dl.trade
• benchm.ml
• dl.java
• dl.tf
• self-car.ai
• dql
• drl.berkeley
• PAIR-code
• fast.ai
• courses.fast.ai
• cs231n.stanford.edu/
• cs224d.stanford.edu/
• oxford-cs-deepnlp-2017
• UFLDL Tutorial 1
• UFLDL Tutorial 2
• dl.NLP (without Magic)|
• dl.p.dn
• dl.bu
• Theano.tut
• nn.Matlab
• cnn.face
• Torch7.tut
• ml.tut.web
• VGG.cnn
• TensorFlow.tut
• TensorFlow.tut+
• TensorFlow.py.n
• Keras.Lasagne.tut
• TensorFlow.LSTM.RNN
• TensorFlow.World
• dl.py
• Grokking.dl
• dl.Search
• Keras.tut
• Pytorch.tut
• Ray Kurzweil
• Andrew Ng
• Geoff Hinton
• Yann LeCun
• Yoshua bengio
• Jeff Hawkins
• Adam Coates
• Adam Coates
• Adam Coates
• Yann LeCun
• Geoffrey Hinton at GoogleTechTalks
• Jeremy Howard at TEDxBrussels
• Andrew Ng in Stanford (2011)
• Chris Manning in Stanford
• Natalie Hammel and Lorraine Yurshansky
• Steve Jurvetson (and panel) at VLAB in Stanford
• Leo Isikdogan at Motorola Mobility HQ
• CS224u: Natural Language Understanding
• Deep Learning – a cookbook view

---

ML/DL conferences in 2018

• aideadlin.es
• /r/MachineLearning/
• conference paper templates
• AI Conferences in 2018
• Calendar of Computer Image Analysis, Computer Vision Conferences
• guide2research

Conference Papers:

• JMLR Papers list
• JAIR Paper list
• Google Scholar AI track
• KDD explorations
• CVPR Open Access

---

---

---

highscalability - to dive in all time favorites list

• [Week-1] 19-Nov-2017
• [Week-2] 26-Nov-2017
• [Week-3] 03-Dec-2017
• [Week-4] 10-Dec-2017
• [Week-5] 17-Dec-2017
• [Week-6] 24-Dec-2017
• [Week-7] 31-Dec-2017
• [startupreadings]
• [awesome-scalability]

---

Blockchain	Ethereum	Bitcoin	LTC	Neo	QTUM	UBIQ

• [Week-1] 19-Nov-2017 - decentralized systems(Blockchain)
• [Week-2] 26-Nov-2017 - decentralized systems(Blockchain)
• [Week-3] 03-Dec-2017 - bitcoin content
• [Week-4] 17-Dec-2017 - bitcoin code
• [Week-5] 24-Dec-2017 - ethereum content
• [Week-6] 31-Dec-2017 - ethereum programming + ICO

---

|| blockchain-papers | blockchain in action | awesome-blockchain+influencers+whitepapers+cryptocurrency | ICO+Resources||

---

---

Maintainer

Gopala KR / @gopala-kr