Practical Block-wise Neural Network Architecture Generation
Zhao Zhong, Junjie Yan, Wei Wu, Jing Shao, Cheng-Lin Liu
Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it performs competitive results in comparison to the hand-crafted state-of-the-art networks on image classification, additionally, the best network generated by BlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing auto-generate networks. (2) in the meanwhile, it offers tremendous reduction of the search space in designing networks which only spends 3 days with 32 GPUs, and (3) moreover, it has strong generalizability that the network built on CIFAR also performs well on a larger-scale ImageNet dataset.
@article{DBLP:journals/corr/abs-1708-05552, author = {Zhao Zhong and Junjie Yan and Cheng{-}Lin Liu}, title = {Practical Network Blocks Design with Q-Learning}, journal = {CoRR}, volume = {abs/1708.05552}, year = {2017}, url = {http://arxiv.org/abs/1708.05552}, archivePrefix = {arXiv}, eprint = {1708.05552}, timestamp = {Mon, 13 Aug 2018 16:47:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1708-05552.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }