Making use of population information in evolutionary artificial neural networks

Xin YAO, Yong LIU

Research output: Journal PublicationsJournal Article (refereed)peer-review

210 Citations (Scopus)

Abstract

This paper is concerned with the simultaneous evolution of artificial neural network (ANN) architectures and weights. The current practice in evolving ANN's is to choose the best ANN in the last generation as the final result. This paper proposes a different approach to form the final result by combining all the individuals in the last generation in order to make best use of all the information contained in the whole population. This approach regards a population of ANN's as an ensemble and uses a combination method to integrate them. Although there has been some work on integrating ANN modules [2], [3], little has been done in evolutionary learning to make best use of its population information. Four linear combination methods have been investigated in this paper to illustrate our ideas. Three real-world data sets have been used in our experimental studies, which show that the recursive least-square (RLS) algorithm always produces an integrated system that outperforms the best individual. The results confirm that a population contains more information than a single individual. Evolutionary learning should exploit such information to improve generalization of learned systems. © 1998 IEEE.
Original languageEnglish
Pages (from-to)417-425
Number of pages9
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume28
Issue number3
DOIs
Publication statusPublished - Jun 1998
Externally publishedYes

Bibliographical note

This work was supported in part by the Australian Research Council through its small grant scheme.

Keywords

  • Behavioral evolution
  • Evolutionary artificial neural networks
  • Evolutionary programming
  • Module combination
  • Population-based learning

Fingerprint

Dive into the research topics of 'Making use of population information in evolutionary artificial neural networks'. Together they form a unique fingerprint.

Cite this