Research and Verification of Convolutional Neural Network Lightweight in BCI
Joint Authors
Xu, Shipu
Li, Runlong
Wang, Yunsheng
Liu, Yong
Hu, Wenwen
Wu, Yingjing
Zhang, Chenxi
Liu, Chang
Ma, Chao
Source
Computational and Mathematical Methods in Medicine
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-08-01
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
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%.
American Psychological Association (APA)
Xu, Shipu& Li, Runlong& Wang, Yunsheng& Liu, Yong& Hu, Wenwen& Wu, Yingjing…[et al.]. 2020. Research and Verification of Convolutional Neural Network Lightweight in BCI. Computational and Mathematical Methods in Medicine،Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1139495
Modern Language Association (MLA)
Xu, Shipu…[et al.]. Research and Verification of Convolutional Neural Network Lightweight in BCI. Computational and Mathematical Methods in Medicine No. 2020 (2020), pp.1-11.
https://search.emarefa.net/detail/BIM-1139495
American Medical Association (AMA)
Xu, Shipu& Li, Runlong& Wang, Yunsheng& Liu, Yong& Hu, Wenwen& Wu, Yingjing…[et al.]. Research and Verification of Convolutional Neural Network Lightweight in BCI. Computational and Mathematical Methods in Medicine. 2020. Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1139495
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1139495