Learning of neural network parameters using a fuzzy genetic algorithm

S. H. Ling; H. K. Lam; Hung Fat Frank Leung; P. K S Tam

doi:10.1109/CEC.2002.1004538

Learning of neural network parameters using a fuzzy genetic algorithm

S. H. Ling, H. K. Lam, Hung Fat Frank Leung, P. K S Tam

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

9 Citations (Scopus)

Abstract

This paper presents the learning of neural network parameters using a fuzzy genetic algorithm (GA). The proposed fuzzy GA is modified from the traditional GA with arithmetic crossover and non-uniform mutation. By introducing modified genetic operations, it will be shown that the performance of the proposed fuzzy GA are better than the traditional GA based on some benchmark test functions. Using the fuzzy GA, the parameters of the neural networks can be tuned. An application example on sunspot forecasting is given to show the merits of the proposed fuzzy GA.

Original language	English
Title of host publication	Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002
Publisher	IEEE Computer Society
Pages	1928-1933
Number of pages	6
Volume	2
ISBN (Print)	0780372824, 9780780372825
DOIs	https://doi.org/10.1109/CEC.2002.1004538
Publication status	Published - 1 Jan 2002
Event	2002 Congress on Evolutionary Computation, CEC 2002 - Honolulu, HI, United States Duration: 12 May 2002 → 17 May 2002

Conference

Conference	2002 Congress on Evolutionary Computation, CEC 2002
Country/Territory	United States
City	Honolulu, HI
Period	12/05/02 → 17/05/02

ASJC Scopus subject areas

Software

More information

10.1109/CEC.2002.1004538

Cite this

@inproceedings{870cac0e4fdb4da48987db0a57b67ee0,

title = "Learning of neural network parameters using a fuzzy genetic algorithm",

abstract = "This paper presents the learning of neural network parameters using a fuzzy genetic algorithm (GA). The proposed fuzzy GA is modified from the traditional GA with arithmetic crossover and non-uniform mutation. By introducing modified genetic operations, it will be shown that the performance of the proposed fuzzy GA are better than the traditional GA based on some benchmark test functions. Using the fuzzy GA, the parameters of the neural networks can be tuned. An application example on sunspot forecasting is given to show the merits of the proposed fuzzy GA.",

author = "Ling, {S. H.} and Lam, {H. K.} and Leung, {Hung Fat Frank} and Tam, {P. K S}",

year = "2002",

month = jan,

day = "1",

doi = "10.1109/CEC.2002.1004538",

language = "English",

isbn = "0780372824",

volume = "2",

pages = "1928--1933",

booktitle = "Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002",

publisher = "IEEE Computer Society",

address = "United States",

note = "2002 Congress on Evolutionary Computation, CEC 2002 ; Conference date: 12-05-2002 Through 17-05-2002",

}

Ling, SH, Lam, HK, Leung, HFF & Tam, PKS 2002, Learning of neural network parameters using a fuzzy genetic algorithm. in Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002. vol. 2, 1004538, IEEE Computer Society, pp. 1928-1933, 2002 Congress on Evolutionary Computation, CEC 2002, Honolulu, HI, United States, 12/05/02. https://doi.org/10.1109/CEC.2002.1004538

Learning of neural network parameters using a fuzzy genetic algorithm. / Ling, S. H.; Lam, H. K.; Leung, Hung Fat Frank; Tam, P. K S.

Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002. Vol. 2 IEEE Computer Society, 2002. p. 1928-1933 1004538.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Learning of neural network parameters using a fuzzy genetic algorithm

AU - Ling, S. H.

AU - Lam, H. K.

AU - Leung, Hung Fat Frank

AU - Tam, P. K S

PY - 2002/1/1

Y1 - 2002/1/1

N2 - This paper presents the learning of neural network parameters using a fuzzy genetic algorithm (GA). The proposed fuzzy GA is modified from the traditional GA with arithmetic crossover and non-uniform mutation. By introducing modified genetic operations, it will be shown that the performance of the proposed fuzzy GA are better than the traditional GA based on some benchmark test functions. Using the fuzzy GA, the parameters of the neural networks can be tuned. An application example on sunspot forecasting is given to show the merits of the proposed fuzzy GA.

AB - This paper presents the learning of neural network parameters using a fuzzy genetic algorithm (GA). The proposed fuzzy GA is modified from the traditional GA with arithmetic crossover and non-uniform mutation. By introducing modified genetic operations, it will be shown that the performance of the proposed fuzzy GA are better than the traditional GA based on some benchmark test functions. Using the fuzzy GA, the parameters of the neural networks can be tuned. An application example on sunspot forecasting is given to show the merits of the proposed fuzzy GA.

UR - http://www.scopus.com/inward/record.url?scp=24844455257&partnerID=8YFLogxK

U2 - 10.1109/CEC.2002.1004538

DO - 10.1109/CEC.2002.1004538

M3 - Conference article published in proceeding or book

SN - 0780372824

SN - 9780780372825

VL - 2

SP - 1928

EP - 1933

BT - Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002

PB - IEEE Computer Society

T2 - 2002 Congress on Evolutionary Computation, CEC 2002

Y2 - 12 May 2002 through 17 May 2002

ER -

Learning of neural network parameters using a fuzzy genetic algorithm

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Cite this