DP-Net: Dynamic Programming Guided Deep Neural Network Compression

Abstract

In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an optimization process to train a clustering-friendly DNN. Experiments showed that the DP-Net allows larger compression than the state-of-the-art counterparts while preserving accuracy. The largest 77X compression ratio on Wide ResNet is achieved by combining DP-Net with other compression techniques. Furthermore, the DP-Net is extended for compressing a robust DNN model with negligible accuracy loss. At last, a custom accelerator is designed on FPGA to speed up the inference computation with DP-Net.

7pages, 4 figures

References in corpus (10)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Compressing Deep Convolutional Networks using Vector Quantization
• Rethinking the Value of Network Pruning
• Theoretically Principled Trade-off between Robustness and Accuracy
• Binarized Neural Networks
• Compressing Neural Networks with the Hashing Trick
• Ultimate tensorization: compressing convolutional and FC layers alike
• Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
• Soft Weight-Sharing for Neural Network Compression