Studying the Effects of Dual Coding on the Adaptation of Representation for Linkage in Evolutionary Algorithms

Abstract : For successful and efficient use of GAs, it is not enough to simply apply simple GAs (SGAs). In addition, it is necessary to find a proper representation for the problem and to integrate linkage information about the problem structure. Similarly, it is important to develop appropriate search operators that fit well to the properties of the genotype encoding and that can learn linkage information to assisst in creating and not in destroying the building blocks. Besides, the representation must at least be able to encode all possible solutions of an optimization problem, and genetic operators such as crossover and mutation should be applicable to it. In this chapter, sequential alternation strategies between two coding schemes are formulated in the framework of dynamic change of genotype encoding in GAs for function optimization. Likewise, new variants of GAs for difficult optimization problems are developed using a parallel implementation of GAs and evolving a dynamic exchange of individual representation in the context of dual coding concepts. Numerical experiments show that the evolved proposals significantly outperform a SGA with static single coding.
Type de document :
Chapitre d'ouvrage
Chen, Ying-ping and Lim, Meng-Hiot. Linkage in Evolutionary Computation, Springer Berlin / Heidelberg, pp.249-284, 2008, Studies in Computational Intelligence, <10.1007/978-3-540-85068-7>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00331863
Contributeur : Sébastien Verel <>
Soumis le : samedi 18 octobre 2008 - 17:45:56
Dernière modification le : lundi 23 février 2009 - 16:55:19

Identifiants

Collections

Citation

Maroun Bercachi, Philippe Collard, Manuel Clergue, Sébastien Verel. Studying the Effects of Dual Coding on the Adaptation of Representation for Linkage in Evolutionary Algorithms. Chen, Ying-ping and Lim, Meng-Hiot. Linkage in Evolutionary Computation, Springer Berlin / Heidelberg, pp.249-284, 2008, Studies in Computational Intelligence, <10.1007/978-3-540-85068-7>. <hal-00331863>

Partager

Métriques

Consultations de la notice

115