Evolving multiple neural networks

Sunghwan Sohn, Cihan H. Dagli

Research output: Contribution to conferencePaperpeer-review

1 Scopus citations

Abstract

In this paper we apply genetic algorithms to the automatic generation of neural networks as well as the biological inspiration of neural networks to successfully adapt to environments. The network produced by this method can be customized for a special objective because the network is selected by the objective function. The final goal in designing a classifier is to achieve the best performance for a given classification. It has been observed that some methods of combining networks consistently outperform a single network. Therefore, we also investigate the performance of combining multiple evolving neural networks. Financial and medical data are used to test the network's performance.

Original languageEnglish (US)
Pages9-14
Number of pages6
StatePublished - Dec 1 2002
EventProceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design - St. Louis, MO, United States
Duration: Nov 10 2002Nov 13 2002

Other

OtherProceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design
CountryUnited States
CitySt. Louis, MO
Period11/10/0211/13/02

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Evolving multiple neural networks'. Together they form a unique fingerprint.

Cite this