A Study of Neutrality of Boolean Function Landscapes in Genetic Programming

Abstract : Neutrality of genetic programming Boolean function landscapes is investigated in this paper. Compared with some well known contributions on the same issue, we define new measures that help characterizing neutral landscapes, we use a new sampling methodology, which captures features that are disregarded by uniform random sampling, we introduce new genetic operators to define the neighborhood of tree structures and we compare the fitness landscape induced by different sets of functional operators. This study indicates the existence of a relationship between our neutrality measures and the performance of genetic programming for the problems studied.
Type de document :
Article dans une revue
Journal of Theoretical Computer Science (TCS), Elsevier, 2012, 425, pp.34 -- 57. <10.1016/j.tcs.2011.03.011>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00563462
Contributeur : Sébastien Verel <>
Soumis le : samedi 5 février 2011 - 12:32:09
Dernière modification le : samedi 16 janvier 2016 - 01:10:22

Identifiants

Citation

Leonardo Vanneschi, Yuri Pirola, Giancarlo Mauri, Philippe Collard, Sébastien Verel. A Study of Neutrality of Boolean Function Landscapes in Genetic Programming. Journal of Theoretical Computer Science (TCS), Elsevier, 2012, 425, pp.34 -- 57. <10.1016/j.tcs.2011.03.011>. <hal-00563462>

Partager

Métriques

Consultations de la notice

147