UM  > 科技學院  > 電腦及資訊科學系
Kernel-Based Multilayer Extreme Learning Machines for Representation Learning
Wong, Chi Man1; Vong, Chi Man1; Wong, Pak Kin2; Cao, Jiuwen3
2018-03
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X
Volume29Issue:3Pages:757-762
Abstract

Recently, multilayer extreme learning machine (ML-ELM) was applied to stacked autoencoder (SAE) for representation learning. In contrast to traditional SAE, the training time of ML-ELM is significantly reduced from hours to seconds with high accuracy. However, ML-ELM suffers from several drawbacks: 1) manual tuning on the number of hidden nodes in every layer is an uncertain factor to training time and generalization; 2) random projection of input weights and bias in every layer of ML-ELM leads to suboptimal model generalization; 3) the pseudoinverse solution for output weights in every layer incurs relatively large reconstruction error; and 4) the storage and execution time for transformation matrices in representation learning are proportional to the number of hidden layers. Inspired by kernel learning, a kernel version of ML-ELM is developed, namely, multilayer kernel ELM (ML-KELM), whose contributions are: 1) elimination of manual tuning on the number of hidden nodes in every layer; 2) no random projection mechanism so as to obtain optimal model generalization; 3) exact inverse solution for output weights is guaranteed under invertible kernel matrix, resulting to smaller reconstruction error; and 4) all transformation matrices are unified into two matrices only, so that storage can be reduced and may shorten model execution time. Benchmark data sets of different sizes have been employed for the evaluation of ML-KELM. Experimental results have verified the contributions of the proposed ML-KELM. The improvement in accuracy over benchmark data sets is up to 7%.

KeywordKernel Learning Multilayer Extreme Learning Machine (Ml-elm) Representation Learning Stacked Autoencoder (Sae)
DOI10.1109/TNNLS.2016.2636834
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000426344600023
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
The Source to ArticleWOS
Fulltext Access
Citation statistics
Cited Times [WOS]:17   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
DEPARTMENT OF ELECTROMECHANICAL ENGINEERING
Affiliation1.Department of Computer and Information Science, University of Macau, Macau, China, 999078
2.Department of Electromechanical Engineering, University of Macau, Macau, China, 999078
3.Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China, 310018
First Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Wong, Chi Man,Vong, Chi Man,Wong, Pak Kin,et al. Kernel-Based Multilayer Extreme Learning Machines for Representation Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(3):757-762.
APA Wong, Chi Man,Vong, Chi Man,Wong, Pak Kin,&Cao, Jiuwen.(2018).Kernel-Based Multilayer Extreme Learning Machines for Representation Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(3),757-762.
MLA Wong, Chi Man,et al."Kernel-Based Multilayer Extreme Learning Machines for Representation Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.3(2018):757-762.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wong, Chi Man]'s Articles
[Vong, Chi Man]'s Articles
[Wong, Pak Kin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wong, Chi Man]'s Articles
[Vong, Chi Man]'s Articles
[Wong, Pak Kin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wong, Chi Man]'s Articles
[Vong, Chi Man]'s Articles
[Wong, Pak Kin]'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.