UM  > 科技學院  > 電腦及資訊科學系
Optimize real-valued RBM with Bidirectional Autoencoder
Feng Q.; Chen L.; Chen C.L.P.
2016-01-25
Conference NameInternational Conference on Fuzzy Theory and Its Applications (IFUZZY)
Source PublicationiFUZZY 2015 - 2015 International Conference on Fuzzy Theory and Its Applications, Conference Digest
Pages22-27
Conference DateNOV 18-20, 2015
Conference PlaceYilan, TAIWAN
Abstract

Deep learning increasingly attracted attention after the fast training method of Restricted Boltzmann Machine(RBM) isproposed[1]. Many researches directly constructed deep architecture with stack RBMs to learn the representation of the data, few studied the optimization method to get good RBM parameters. Here proposes a new optimization method for real-valued RBM by minimizing the reconstructed error. Firstly, build and initialize Bidirectional Autoencoder(Bi-Ae). Secondly, minimize the cost function with Stochastic Gradient Descent (SGD) to get the parameters. Thirdly, convert the Bi-AE into RBM with the most suitable parameters. Experiments are executed on the MNIST dataset. Compared with PSO and likelihood maximum optimization methods, the reconstructed errors of the proposed method is 4.02% smaller than the result from error[1], which is advanced.

KeywordBack Propagation Bidirectional Autoencoder Rbm Optimization Sgd
DOI10.1109/iFUZZY.2015.7391888
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000380618900005
Fulltext Access
Citation statistics
Cited Times [WOS]:1   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
AffiliationUniversidade de Macau
Recommended Citation
GB/T 7714
Feng Q.,Chen L.,Chen C.L.P.. Optimize real-valued RBM with Bidirectional Autoencoder[C],2016:22-27.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Feng Q.]'s Articles
[Chen L.]'s Articles
[Chen C.L.P.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Feng Q.]'s Articles
[Chen L.]'s Articles
[Chen C.L.P.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Feng Q.]'s Articles
[Chen L.]'s Articles
[Chen C.L.P.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.