Evolving a cooperative population of neural networks by minimizing mutual information

Yong LIU, Xin YAO, Qiangfu ZHAO, T. HIGUCHI

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

24 Citations (Scopus)

Abstract

Evolutionary ensembles with negative correlation learning (EENCL) is an evolutionary learning system for learning and designing neural network ensembles. The fitness sharing used in EENCL was based on the idea of "covering" the same training patterns by shared individuals. This paper explores connection between fitness sharing and information concept, and introduces mutual information into EENCL. Through minimization of mutual information, a diverse and cooperative population of neural networks can be evolved by EENCL. The effectiveness of such evolutionary learning approach was tested on two real-world problems.
Original languageEnglish
Title of host publicationProceedings of the 2001 Congress on Evolutionary Computation
PublisherIEEE
Pages384-389
Number of pages6
Volume2
ISBN (Print)0780366573
DOIs
Publication statusPublished - 2001
Externally publishedYes

Fingerprint

Dive into the research topics of 'Evolving a cooperative population of neural networks by minimizing mutual information'. Together they form a unique fingerprint.

Cite this