标题:The effect of different hidden unit number of sparse autoencoder
作者:Xu, Qingyang ;Zhang, Li
作者机构:[Xu, Qingyang ;Zhang, Li ] School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China
会议名称:27th Chinese Control and Decision Conference, CCDC 2015
会议日期:23 May 2015 through 25 May 2015
来源:Proceedings of the 2015 27th Chinese Control and Decision Conference, CCDC 2015
出版年:2015
页码:2464-2467
DOI:10.1109/CCDC.2015.7162335
关键词:Backpropagation; Different hidden unit number; MNIST database; Sparse autoencoder
摘要:Sparse autoencoder is the fundamental part in some deep architecture. The hidden layer output is the compression of the input data which gives a better representation of the input than the original raw input. However, the determination of hidden unit number is always experiential. In this paper, the different hidden unit number is discussed. The weight of sparse autoencoder will learn the digital number outline of the handwriting instead of pen strokes when the hidden unit number is smaller. The weight can learn the pen strokes of the handwriting when the hidden unit number is larger. © 2015 IEEE.
收录类别:EI;SCOPUS
Scopus被引频次:3
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84945549860&doi=10.1109%2fCCDC.2015.7162335&partnerID=40&md5=11eaec0927bf49671c8478d0a109b47d
TOP