Noise resistant training for extreme learning machine

Yik Lam Lui; Hiu Tung Wong; Chi-Sing Leung; Sam Kwong

doi:10.1007/978-3-319-59081-3_31

Noise resistant training for extreme learning machine

Yik Lam Lui, Hiu Tung Wong, Chi-Sing Leung^*, Sam Kwong

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

The extreme learning machine (ELM) concept provides some effective training algorithms to construct single hidden layer feedforward networks (SHLFNs). However, the conventional ELM algorithms were designed for the noiseless situation only, in which the outputs of the hidden nodes are not contaminated by noise. This paper presents two noise-resistant training algorithms, namely noise-resistant incremental ELM (NRI-ELM) and noise-resistant convex incremental ELM (NRCI-ELM). For NRI-ELM, its noise-resistant ability is better than that of the conventional incremented ELM algorithms. To further enhance the noise resistant ability, the NRCI-ELM algorithm is proposed. The convergent properties of the two proposed noise resistant algorithms are also presented.

Original language	English
Title of host publication	Advances in Neural Networks - ISNN 2017
Subtitle of host publication	14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II
Publisher	Springer Nature
Pages	257-265
ISBN (Print)	9783319590806
DOIs	https://doi.org/10.1007/978-3-319-59081-3_31
Publication status	Published - 2017
Event	14th International Symposium on Neural Networks (ISNN 2017) - Hokkaido University, Sapporo, Japan Duration: 21 Jun 2017 → 26 Jun 2017

Publication series

Name	Lecture Notes in Computer Science
Volume	10262 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	14th International Symposium on Neural Networks (ISNN 2017)
Abbreviated title	ISNN 2017
Country/Territory	Japan
City	Sapporo
Period	21/06/17 → 26/06/17

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Research Keywords

Node noise
Extreme learning machines
Incremental algorithm

Access Output

10.1007/978-3-319-59081-3_31

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Lui, Y. L., Wong, H. T., Leung, C.-S., & Kwong, S. (2017). Noise resistant training for extreme learning machine. In Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II (pp. 257-265). (Lecture Notes in Computer Science; Vol. 10262 LNCS). Springer Nature. https://doi.org/10.1007/978-3-319-59081-3_31

@inproceedings{71aa6b775ee94334a2cc6d5add1748de,

title = "Noise resistant training for extreme learning machine",

abstract = "The extreme learning machine (ELM) concept provides some effective training algorithms to construct single hidden layer feedforward networks (SHLFNs). However, the conventional ELM algorithms were designed for the noiseless situation only, in which the outputs of the hidden nodes are not contaminated by noise. This paper presents two noise-resistant training algorithms, namely noise-resistant incremental ELM (NRI-ELM) and noise-resistant convex incremental ELM (NRCI-ELM). For NRI-ELM, its noise-resistant ability is better than that of the conventional incremented ELM algorithms. To further enhance the noise resistant ability, the NRCI-ELM algorithm is proposed. The convergent properties of the two proposed noise resistant algorithms are also presented.",

keywords = "Node noise, Extreme learning machines, Incremental algorithm",

author = "Lui, {Yik Lam} and Wong, {Hiu Tung} and Chi-Sing Leung and Sam Kwong",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; 14th International Symposium on Neural Networks (ISNN 2017), ISNN 2017 ; Conference date: 21-06-2017 Through 26-06-2017",

year = "2017",

doi = "10.1007/978-3-319-59081-3_31",

language = "English",

isbn = "9783319590806",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "257--265",

booktitle = "Advances in Neural Networks - ISNN 2017",

address = "United States",

}

Lui, YL, Wong, HT , Leung, C-S & Kwong, S 2017, Noise resistant training for extreme learning machine. in Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II. Lecture Notes in Computer Science, vol. 10262 LNCS, Springer Nature, pp. 257-265, 14th International Symposium on Neural Networks (ISNN 2017), Sapporo, Japan, 21/06/17. https://doi.org/10.1007/978-3-319-59081-3_31

Noise resistant training for extreme learning machine. / Lui, Yik Lam; Wong, Hiu Tung ; Leung, Chi-Sing et al.
Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II. Springer Nature, 2017. p. 257-265 (Lecture Notes in Computer Science; Vol. 10262 LNCS).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Noise resistant training for extreme learning machine

AU - Lui, Yik Lam

AU - Wong, Hiu Tung

AU - Leung, Chi-Sing

AU - Kwong, Sam

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2017

Y1 - 2017

N2 - The extreme learning machine (ELM) concept provides some effective training algorithms to construct single hidden layer feedforward networks (SHLFNs). However, the conventional ELM algorithms were designed for the noiseless situation only, in which the outputs of the hidden nodes are not contaminated by noise. This paper presents two noise-resistant training algorithms, namely noise-resistant incremental ELM (NRI-ELM) and noise-resistant convex incremental ELM (NRCI-ELM). For NRI-ELM, its noise-resistant ability is better than that of the conventional incremented ELM algorithms. To further enhance the noise resistant ability, the NRCI-ELM algorithm is proposed. The convergent properties of the two proposed noise resistant algorithms are also presented.

AB - The extreme learning machine (ELM) concept provides some effective training algorithms to construct single hidden layer feedforward networks (SHLFNs). However, the conventional ELM algorithms were designed for the noiseless situation only, in which the outputs of the hidden nodes are not contaminated by noise. This paper presents two noise-resistant training algorithms, namely noise-resistant incremental ELM (NRI-ELM) and noise-resistant convex incremental ELM (NRCI-ELM). For NRI-ELM, its noise-resistant ability is better than that of the conventional incremented ELM algorithms. To further enhance the noise resistant ability, the NRCI-ELM algorithm is proposed. The convergent properties of the two proposed noise resistant algorithms are also presented.

KW - Node noise

KW - Extreme learning machines

KW - Incremental algorithm

UR - http://www.scopus.com/inward/record.url?scp=85021733548&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85021733548&origin=recordpage

U2 - 10.1007/978-3-319-59081-3_31

DO - 10.1007/978-3-319-59081-3_31

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9783319590806

T3 - Lecture Notes in Computer Science

SP - 257

EP - 265

BT - Advances in Neural Networks - ISNN 2017

PB - Springer Nature

T2 - 14th International Symposium on Neural Networks (ISNN 2017)

Y2 - 21 June 2017 through 26 June 2017

ER -

Lui YL, Wong HT , Leung CS , Kwong S. Noise resistant training for extreme learning machine. In Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II. Springer Nature. 2017. p. 257-265. (Lecture Notes in Computer Science). Epub 2017 May 31. doi: 10.1007/978-3-319-59081-3_31

Noise resistant training for extreme learning machine

Abstract

Publication series

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this