期刊
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
卷 40, 期 8, 页码 1640-1647出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCAD.2020.3019993
关键词
Convolution; convolutional neural network (CNN); memristor; weight pruning
类别
资金
- Natural Science Foundation of China [61673187]
- NPRP from Qatar National Research Fund [NPRP 9-466-1-103]
The article introduces a new convolution algorithm called CKFO, which addresses the issue of unchanged computation after weight pruning in convolutional neural networks. Through experimentation, it has been shown that the model is able to reduce parameters and multiplication operations while maintaining high accuracy.
This article presents a new convolution algorithm: convolution kernel first operated (CKFO), which can solve the problem that the actual calculation is not reduced after pruning the weight of the convolution neural network. According to the convolution algorithm, this article proposes a simulated memristor implementation of a convolutional neural network (CNN). After that, we use the method of ex-situ training to train CNN in Tensorflow and then download the trained parameters to the Simulink system by compiling the conductance value of memristor to test the proposed simulation model. Finally, the effectiveness of the proposed model is verified. In addition, we prune the weights of CNN and retrain it, then adjust the simulation model according to the parameters after being pruned. We are surprised to find that the convolution layer designed according to the new convolution algorithm can apply the results of the pruned weight without any modification to the circuit, which is very cumbersome in other memristor-based CNN because the distribution of the pruned weight is irregular. The parameters are reduced by 75.24% and the number of multiplication operations in the convolution layer was reduced by 30.1%, while the accuracy is just reduced by 0.06%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据