ECAI 2004 Conference Paper

[PDF] [full paper] [prev] [tofc] [next]

A Genetic Algorithm with Feminine Selection

Josué Pereira de Castro, Adriana Postal, Guilherme Bittencourt

This paper describes a selection approach for evolutionary algorithms - called feminine selection -- that is inspired in the fact that in some animal species the female actively select their reproduction partners. In these species, the males exhibit their attributes, sometimes fighting with other males, and the female choose the one she considers the best. To implement this approach, the algorithm adopts a sexual reproduction mechanism, that among other properties precludes the reproduction between two identical genomes, avoiding premature convergence. The proposed algorithm was implemented and its results compared with those of the standard Goldberg algorithm.

Keywords: Genetic Algorithms

Citation: Josué Pereira de Castro, Adriana Postal, Guilherme Bittencourt: A Genetic Algorithm with Feminine Selection. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.244-248.

[prev] [tofc] [next]

ECAI-2004 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the Universitat Politècnica de València on behalf of Asociación Española de Inteligencia Artificial (AEPIA) and Associació Catalana d'Intel-ligència Artificial (ACIA).