Compact Neural Representation Using Attentive Network Pruning

Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and memory complexity of deep networks. We propose to examine the ability of attentive connection pruning to deal with redundancy reduction in neural networks as a contribution to the reduction of computational demand. In this work, we describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers. Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation. We conduct experiments using different network architectures on popular benchmark datasets to show high compression ratio is achievable with negligible loss of accuracy.

[1]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[2]  Yurong Chen,et al.  Dynamic Network Surgery for Efficient DNNs , 2016, NIPS.

[3]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[4]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[5]  Misha Denil,et al.  Predicting Parameters in Deep Learning , 2014 .

[6]  Yiran Chen,et al.  Learning Structured Sparsity in Deep Neural Networks , 2016, NIPS.

[7]  Jianxin Wu,et al.  ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[9]  Xin Dong,et al.  Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon , 2017, NIPS.

[10]  Yixin Chen,et al.  Compressing Neural Networks with the Hashing Trick , 2015, ICML.

[11]  Hassan Foroosh,et al.  Sparse Convolutional Neural Networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Hao Zhou,et al.  Less Is More: Towards Compact CNNs , 2016, ECCV.

[13]  Eunhyeok Park,et al.  Weighted-Entropy-Based Quantization for Deep Neural Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  John K. Tsotsos,et al.  STNet: Selective Tuning of Convolutional Networks for Object Localization , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

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

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[18]  Babak Hassibi,et al.  Second Order Derivatives for Network Pruning: Optimal Brain Surgeon , 1992, NIPS.

[19]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[20]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[21]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[22]  John K. Tsotsos Analyzing vision at the complexity level , 1990, Behavioral and Brain Sciences.