Combining modular neural networks developed by evolutionary algorithm

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

Evolutionary approach to artificial neural networks has been rapidly developing in the recent years and shows a great possibility as a powerful tool. However, most evolutionary neural networks use the simple node as a building block to evolve, and select the only one network producing the best result after evolution. In this paper we present the concepts and methodologies for evolutionary modular neural networks which boost up the overall performance by combining several potential networks emerged in the course of evolution. The experimental result with the recognition problem of handwritten numerals shows the possibility of combining a number of characteristic networks from gene pool.

Original languageEnglish
Pages647-650
Number of pages4
Publication statusPublished - 1997 Jan 1
EventProceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97 - Indianapolis, IN, USA
Duration: 1997 Apr 131997 Apr 16

Other

OtherProceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97
CityIndianapolis, IN, USA
Period97/4/1397/4/16

Fingerprint

Evolutionary algorithms
Neural networks
Genes

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

Cho, S. B. (1997). Combining modular neural networks developed by evolutionary algorithm. 647-650. Paper presented at Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97, Indianapolis, IN, USA, .
Cho, Sung Bae. / Combining modular neural networks developed by evolutionary algorithm. Paper presented at Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97, Indianapolis, IN, USA, .4 p.
@conference{281a64d5a2b64c119a7982b68dbc3334,
title = "Combining modular neural networks developed by evolutionary algorithm",
abstract = "Evolutionary approach to artificial neural networks has been rapidly developing in the recent years and shows a great possibility as a powerful tool. However, most evolutionary neural networks use the simple node as a building block to evolve, and select the only one network producing the best result after evolution. In this paper we present the concepts and methodologies for evolutionary modular neural networks which boost up the overall performance by combining several potential networks emerged in the course of evolution. The experimental result with the recognition problem of handwritten numerals shows the possibility of combining a number of characteristic networks from gene pool.",
author = "Cho, {Sung Bae}",
year = "1997",
month = "1",
day = "1",
language = "English",
pages = "647--650",
note = "Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97 ; Conference date: 13-04-1997 Through 16-04-1997",

}

Cho, SB 1997, 'Combining modular neural networks developed by evolutionary algorithm', Paper presented at Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97, Indianapolis, IN, USA, 97/4/13 - 97/4/16 pp. 647-650.

Combining modular neural networks developed by evolutionary algorithm. / Cho, Sung Bae.

1997. 647-650 Paper presented at Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97, Indianapolis, IN, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Combining modular neural networks developed by evolutionary algorithm

AU - Cho, Sung Bae

PY - 1997/1/1

Y1 - 1997/1/1

N2 - Evolutionary approach to artificial neural networks has been rapidly developing in the recent years and shows a great possibility as a powerful tool. However, most evolutionary neural networks use the simple node as a building block to evolve, and select the only one network producing the best result after evolution. In this paper we present the concepts and methodologies for evolutionary modular neural networks which boost up the overall performance by combining several potential networks emerged in the course of evolution. The experimental result with the recognition problem of handwritten numerals shows the possibility of combining a number of characteristic networks from gene pool.

AB - Evolutionary approach to artificial neural networks has been rapidly developing in the recent years and shows a great possibility as a powerful tool. However, most evolutionary neural networks use the simple node as a building block to evolve, and select the only one network producing the best result after evolution. In this paper we present the concepts and methodologies for evolutionary modular neural networks which boost up the overall performance by combining several potential networks emerged in the course of evolution. The experimental result with the recognition problem of handwritten numerals shows the possibility of combining a number of characteristic networks from gene pool.

UR - http://www.scopus.com/inward/record.url?scp=0030683908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030683908&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030683908

SP - 647

EP - 650

ER -

Cho SB. Combining modular neural networks developed by evolutionary algorithm. 1997. Paper presented at Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97, Indianapolis, IN, USA, .