Genetic algorithms enhanced Kohonen's neural networks

Shyh-Jier Huang, Chuan Chang Hung

Research output: Contribution to conferencePaper

8 Citations (Scopus)

Abstract

A new approach of using genetic algorithms to improve the learning characteristics of Kohonen's neural networks is proposed in this paper. In the proposed scheme, genetic algorithms are applied to decide initial weights in the Kohonen's classifiers. The competitive learning is then applied to train neural networks. The proposed method was tested on the power system static security assessment and travelling salesperson problems. The results were very promising to applications.

Original languageEnglish
Pages708-712
Number of pages5
Publication statusPublished - 1995 Dec 1
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: 1995 Nov 271995 Dec 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95-11-2795-12-01

Fingerprint

Genetic algorithms
Neural networks
Classifiers

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Huang, S-J., & Hung, C. C. (1995). Genetic algorithms enhanced Kohonen's neural networks. 708-712. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .
Huang, Shyh-Jier ; Hung, Chuan Chang. / Genetic algorithms enhanced Kohonen's neural networks. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .5 p.
@conference{7db66e4555e04b77b575f169ce3819a7,
title = "Genetic algorithms enhanced Kohonen's neural networks",
abstract = "A new approach of using genetic algorithms to improve the learning characteristics of Kohonen's neural networks is proposed in this paper. In the proposed scheme, genetic algorithms are applied to decide initial weights in the Kohonen's classifiers. The competitive learning is then applied to train neural networks. The proposed method was tested on the power system static security assessment and travelling salesperson problems. The results were very promising to applications.",
author = "Shyh-Jier Huang and Hung, {Chuan Chang}",
year = "1995",
month = "12",
day = "1",
language = "English",
pages = "708--712",
note = "Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) ; Conference date: 27-11-1995 Through 01-12-1995",

}

Huang, S-J & Hung, CC 1995, 'Genetic algorithms enhanced Kohonen's neural networks', Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95-11-27 - 95-12-01 pp. 708-712.

Genetic algorithms enhanced Kohonen's neural networks. / Huang, Shyh-Jier; Hung, Chuan Chang.

1995. 708-712 Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Genetic algorithms enhanced Kohonen's neural networks

AU - Huang, Shyh-Jier

AU - Hung, Chuan Chang

PY - 1995/12/1

Y1 - 1995/12/1

N2 - A new approach of using genetic algorithms to improve the learning characteristics of Kohonen's neural networks is proposed in this paper. In the proposed scheme, genetic algorithms are applied to decide initial weights in the Kohonen's classifiers. The competitive learning is then applied to train neural networks. The proposed method was tested on the power system static security assessment and travelling salesperson problems. The results were very promising to applications.

AB - A new approach of using genetic algorithms to improve the learning characteristics of Kohonen's neural networks is proposed in this paper. In the proposed scheme, genetic algorithms are applied to decide initial weights in the Kohonen's classifiers. The competitive learning is then applied to train neural networks. The proposed method was tested on the power system static security assessment and travelling salesperson problems. The results were very promising to applications.

UR - http://www.scopus.com/inward/record.url?scp=0029488148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029488148&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029488148

SP - 708

EP - 712

ER -

Huang S-J, Hung CC. Genetic algorithms enhanced Kohonen's neural networks. 1995. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .