Exploiting diversity of neural ensembles with speciated evolution

S. I. Lee, J. H. Ahn, S. B. Cho

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

In this paper, we evolve artificial neural networks (ANNs) with speciation and combine them with several methods. In general, an evolving system produces one optimal solution for a given problem. However, we argue that many other solutions exist in the final population, which can improve the overall performance. We propose a new method of evolving multiple speciated neural networks by fitness sharing that helps to optimize multi-objective functions with genetic algorithms, and several combination methods to construct ensembles of ANNs. Experiments with the UCI benchmark datasets show that the proposed methods can produce more speciated ANNs and, thus, improve the performance by combining representative individuals with combination methods.

Original languageEnglish
Pages808-813
Number of pages6
Publication statusPublished - 2001 Jan 1
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CountryUnited States
CityWashington, DC
Period01/7/1501/7/19

Fingerprint

Neural networks
Genetic algorithms
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Lee, S. I., Ahn, J. H., & Cho, S. B. (2001). Exploiting diversity of neural ensembles with speciated evolution. 808-813. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.
Lee, S. I. ; Ahn, J. H. ; Cho, S. B. / Exploiting diversity of neural ensembles with speciated evolution. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.6 p.
@conference{ded9bbd7a3f54ed99ec0a65f0a503bd3,
title = "Exploiting diversity of neural ensembles with speciated evolution",
abstract = "In this paper, we evolve artificial neural networks (ANNs) with speciation and combine them with several methods. In general, an evolving system produces one optimal solution for a given problem. However, we argue that many other solutions exist in the final population, which can improve the overall performance. We propose a new method of evolving multiple speciated neural networks by fitness sharing that helps to optimize multi-objective functions with genetic algorithms, and several combination methods to construct ensembles of ANNs. Experiments with the UCI benchmark datasets show that the proposed methods can produce more speciated ANNs and, thus, improve the performance by combining representative individuals with combination methods.",
author = "Lee, {S. I.} and Ahn, {J. H.} and Cho, {S. B.}",
year = "2001",
month = "1",
day = "1",
language = "English",
pages = "808--813",
note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

Lee, SI, Ahn, JH & Cho, SB 2001, 'Exploiting diversity of neural ensembles with speciated evolution', Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States, 01/7/15 - 01/7/19 pp. 808-813.

Exploiting diversity of neural ensembles with speciated evolution. / Lee, S. I.; Ahn, J. H.; Cho, S. B.

2001. 808-813 Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Exploiting diversity of neural ensembles with speciated evolution

AU - Lee, S. I.

AU - Ahn, J. H.

AU - Cho, S. B.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - In this paper, we evolve artificial neural networks (ANNs) with speciation and combine them with several methods. In general, an evolving system produces one optimal solution for a given problem. However, we argue that many other solutions exist in the final population, which can improve the overall performance. We propose a new method of evolving multiple speciated neural networks by fitness sharing that helps to optimize multi-objective functions with genetic algorithms, and several combination methods to construct ensembles of ANNs. Experiments with the UCI benchmark datasets show that the proposed methods can produce more speciated ANNs and, thus, improve the performance by combining representative individuals with combination methods.

AB - In this paper, we evolve artificial neural networks (ANNs) with speciation and combine them with several methods. In general, an evolving system produces one optimal solution for a given problem. However, we argue that many other solutions exist in the final population, which can improve the overall performance. We propose a new method of evolving multiple speciated neural networks by fitness sharing that helps to optimize multi-objective functions with genetic algorithms, and several combination methods to construct ensembles of ANNs. Experiments with the UCI benchmark datasets show that the proposed methods can produce more speciated ANNs and, thus, improve the performance by combining representative individuals with combination methods.

UR - http://www.scopus.com/inward/record.url?scp=0034876399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034876399&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0034876399

SP - 808

EP - 813

ER -

Lee SI, Ahn JH, Cho SB. Exploiting diversity of neural ensembles with speciated evolution. 2001. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.