A Quantitative Study of Neutrality in GP Boolean Landscapes - Archive ouverte HAL Access content directly
Conference Papers Year : 2006

A Quantitative Study of Neutrality in GP Boolean Landscapes

Abstract

Neutrality of some boolean parity fitness landscapes is investigated in this paper. Compared with some well known contributions on the same issue, we define some new measures that help characterizing neutral landscapes, we use a new sampling methodology, which captures some features that are disregarded by uniform random sampling, and we introduce new genetic operators to define the neighborhood of tree structures. We compare the fitness landscape induced by two different sets of functional operators (SNand and SXorNot). The different characteristics of the neutral networks seem to justify the different difficulties of these landscapes for genetic programming.
Fichier principal
Vignette du fichier
gecco2006_hal_v3.pdf (1.07 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00164691 , version 1 (04-05-2023)

Identifiers

Cite

Leonardo Vanneschi, Yuri Pirola, Philippe Collard, Marco Tomassini, Sébastien Verel, et al.. A Quantitative Study of Neutrality in GP Boolean Landscapes. Proceedings of the 8th annual conference on Genetic and evolutionary computation GECCO '06, Jul 2006, Seatle, United States. pp.895 - 902, ⟨10.1145/1143997.1144152⟩. ⟨hal-00164691⟩
91 View
15 Download

Altmetric

Share

Gmail Facebook X LinkedIn More