Speciated neural networks evolved with fitness sharing technique

J. H. Ahn, S. B. Cho

Research output: Contribution to conferencePaper

12 Citations (Scopus)

Abstract

In order to develop effective evolutionary artificial neural networks (EANNs) we have to address the questions on how to evolve EANNs more efficiently and how to achieve the best performance from the ANNs evolved. Most of the previous works, however, do not utilize all the information obtained with several ANNs but choose the one best network in the last generation. Some recent works indicate that making use of population information by combining ANNs in the last generation can improve the performance, because they can complement each other to construct effective multiple neural networks. In this paper, we propose a new method of evolving multiple speciated neural networks by fitness sharing which helps to optimize multi-objective functions with genetic algorithms. Experiments with the breast cancer data from UCI benchmark datasets show that the proposed method can produce more speciated ANNs and improve the performance by combining the only representative individuals.

Original languageEnglish
Pages390-396
Number of pages7
Publication statusPublished - 2001 Jan 1
EventCongress on Evolutionary Computation 2001 - Soul, Korea, Republic of
Duration: 2001 May 272001 May 30

Other

OtherCongress on Evolutionary Computation 2001
CountryKorea, Republic of
CitySoul
Period01/5/2701/5/30

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

Ahn, J. H., & Cho, S. B. (2001). Speciated neural networks evolved with fitness sharing technique. 390-396. Paper presented at Congress on Evolutionary Computation 2001, Soul, Korea, Republic of.