search for




 

Pruning Method Using Correlation of Weight Changes and Weight Magnitudes in CNN
Int. J. Fuzzy Log. Intell. Syst. 2018;18(4):333-338
Published online December 25, 2018
© 2018 Korean Institute of Intelligent Systems.

Azzaya Nomuunbayar and Sanggil Kang

Department of Computer Engineering, Inha University, Incheon, Korea
Correspondence to: Sanggil Kang (sgkang@inha.ac.kr)
Received September 12, 2018; Revised December 1, 2018; Accepted December 21, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Very complex deep learning models need to be compressed to be memory and cost effective, especially for applications on a mobile platform. We propose a new method of selecting weights to prune to compress convolutional neural networks. To select unimportant weights and get the best result, we combine typical weight magnitude pruning method with our method, which evaluates correlation coefficients of weights to measure the strength of a relationship between weight magnitudes and weight changes through the iterations. In the experimental section, we show our result of pruning 94% of weights in LeNet-5 without significant accuracy loss.
Keywords : Convolutional neural networks, Pruning weights, Weight correlation, Weight change