A Rank Reduced Matrix Method in Extreme Learning Machine

Shuxia LU, Guiqiang ZHANG, Xizhao WANG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

2 Citations (Scopus)

Abstract

Extreme learning machine (ELM) is a learning algorithm for single-hidden layer feedforward neural networks (SLFNs) which randomly chooses hidden nodes and analytically determines the output weights of SLFNs. but when dealing with large datasets, we need more hidden nodes to enhance training and testing accuracy, in this case, this algorithm can't achieve high speed any more, sometimes its training can't be executed because the bias matrix is out of memory. We focus on this issue and use the Rank Reduced Matrix (MMR) method to calculate the hidden layer output matrix, the result showed this method can not only reach much higher speed but also better improve the generalization performance whenever the number of hidden nodes is large or not.

Original languageEnglish
Title of host publicationAdvances in Neural Networks, ISNN 2012 : 9th International Symposium on Neural Networks, Proceedings
EditorsJun WANG, Gary G. YEN, Marios M. POLYCARPOU
PublisherSpringer Berlin
Pages72-79
Number of pages8
ISBN (Print)9783642313455
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event9th International Symposium on Neural Networks, ISNN 2012 - Shenyang, Shenyang, China
Duration: 11 Jul 201214 Jul 2012

Publication series

NameLecture Notes in Computer Science
Volume7367
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference9th International Symposium on Neural Networks, ISNN 2012
Country/TerritoryChina
CityShenyang
Period11/07/1214/07/12

Bibliographical note

This research is supported in part by the National Natural Science Foundation of China (No. 61170040), the Natural Science Foundation of Hebei Province (No. F2011201063, F2010000323), the Plan of the Natural Science Foundation of Hebei University (doctor project) (No.Y2008122).

Keywords

  • Extreme learning machine
  • Rank reduced matrix
  • Singular value decomposition

Fingerprint

Dive into the research topics of 'A Rank Reduced Matrix Method in Extreme Learning Machine'. Together they form a unique fingerprint.

Cite this