UM
Affiliated with RCfalse
Status已發表Published
An Enhanced Hierarchical Extreme Learning Machine with Random Sparse Matrix Based Autoencoder
Wang,Tianlei1; Lai,Xiaoping1; Cao,Jiuwen1; Vong,Chi Man2; Chen,Badong3
2019-05-01
Conference Name44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Source PublicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
Pages3817-3821
Conference DateMAY 12-17, 2019
Conference PlaceBrighton, ENGLAND
Abstract

Recently, by employing the stacked extreme learning machine (ELM) based autoencoders (ELM-AE) and sparse AEs (SAE), multilayer ELM (ML-ELM) and hierarchical ELM (H-ELM) has been developed. Compared to the conventional stacked AEs, the ML-ELM and H-ELM usually achieve better generalization performance with a significantly reduced training time. However, the {ell -1}-norm based SAE may suffer the overfitting problem and it is unable to provide analytical solution leading to long training time for big data. To alleviate these deficiencies, we propose an enhanced H-ELM (EH-ELM) with a novel random sparse matrix based AE (SMA) in this paper. The contributions are in two aspects, 1) utilizing the random sparse matrix, the sparse features can be obtained; 2) the proposed SMA can provide an analytical solution so that the high computational complexity issue in SAE can be addressed. Experimental results on benchmark datasets show that the proposed EH-ELM achieves a higher recognition rate and a faster training speed than H-ELM and ML-ELM.

KeywordAutoencoder Extreme Learning Machine Multilayer Perceptron Random Sparse Matrix.
DOI10.1109/ICASSP.2019.8682337
URLView the original
Indexed ByCPCI-S
Language英語English
WOS Research AreaAcoustics ; Engineering
WOS SubjectAcoustics ; Engineering, Electrical & Electronic
WOS IDWOS:000482554004011
Scopus ID2-s2.0-85069001502
Fulltext Access
Citation statistics
Cited Times [WOS]:4   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionUniversity of Macau
Corresponding AuthorWang,Tianlei
Affiliation1.Institute of Information and Control,Hangzhou Dianzi University,China
2.Faculty of Science and Technology,University of Macau,Macao
3.School of Electronic and Information Engineering,Xi'An Jiaotong University,China
Recommended Citation
GB/T 7714
Wang,Tianlei,Lai,Xiaoping,Cao,Jiuwen,et al. An Enhanced Hierarchical Extreme Learning Machine with Random Sparse Matrix Based Autoencoder[C],2019:3817-3821.
APA Wang,Tianlei,Lai,Xiaoping,Cao,Jiuwen,Vong,Chi Man,&Chen,Badong.(2019).An Enhanced Hierarchical Extreme Learning Machine with Random Sparse Matrix Based Autoencoder.ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,2019-May,3817-3821.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang,Tianlei]'s Articles
[Lai,Xiaoping]'s Articles
[Cao,Jiuwen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang,Tianlei]'s Articles
[Lai,Xiaoping]'s Articles
[Cao,Jiuwen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang,Tianlei]'s Articles
[Lai,Xiaoping]'s Articles
[Cao,Jiuwen]'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.