Practical Block-Wise Neural Network Architecture Generation

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.

[1]  C. Watkins.  Learning from delayed rewards , 1989 .

[2]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[3]  Long-Ji Lin,et al.  Reinforcement learning for robots using neural networks , 1992 .

[4]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[5]  Andrew Y. Ng,et al.  Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping , 1999, ICML.

[6]  Sepp Hochreiter,et al.  Learning to Learn Using Gradient Descent , 2001, ICANN.

[7]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[8]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[9]  Ricardo Vilalta,et al.  A Perspective View and Survey of Meta-Learning , 2002, Artificial Intelligence Review.

[10]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

[11]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[13]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[14]  Marc'Aurelio Ranzato,et al.  Large Scale Distributed Deep Networks , 2012, NIPS.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Aaron Q. Li,et al.  Parameter Server for Distributed Machine Learning , 2013 .

[17]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[18]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[19]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[21]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[22]  Jian Sun,et al.  Convolutional neural networks at constrained time cost , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Trevor Darrell,et al.  Fully convolutional networks for semantic segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[27]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[29]  Frank Hutter,et al.  Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves , 2015, IJCAI.

[30]  Thomas Miconi.  Neural networks with differentiable structure , 2016, ArXiv.

[31]  Jakob Verbeek,et al.  Convolutional Neural Fabrics , 2016, NIPS.

[32]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[33]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[37]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[38]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[39]  Alan L. Yuille,et al.  Genetic CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[40]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[43]  Ramesh Raskar,et al.  Designing Neural Network Architectures using Reinforcement Learning , 2016, ICLR.

[44]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  Masanori Suganuma,et al.  A genetic programming approach to designing convolutional neural network architectures , 2017, GECCO.

[46]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.