Research and Verification of Convolutional Neural Network Lightweight in BCI
Shipu Xu, Runlong Li, Yunsheng Wang, Yong Liu, Wenwen Hu, Yingjing Wu, Chenxi Zhang, Chang Liu, Chao Ma
Source abstract
With the increasing of depth and complexity of the convolutional neural network, parameter dimensionality and volume of computing have greatly restricted its applications. Based on the SqueezeNet network structure, this study introduces a block convolution and uses channel shuffle between blocks to alleviate the information jam. The method is aimed at reducing the dimensionality of parameters of in an original network structure and improving the efficiency of network operation. The verification performance of the ORL dataset shows that the classification accuracy and convergence efficiency are not reduced or even slightly improved when the network parameters are reduced, which supports the validity of block convolution in structure lightweight. Moreover, using a classic CIFAR-10 dataset, this network decreases parameter dimensionality while accelerating computational processing, with excellent convergence stability and efficiency when the network accuracy is only reduced by 1.3%.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.