Springer
Table of ContentsAuthor IndexSearch

Coarse-Graining in Genetic Algorithms: Some Issues and Examples

Andrés Aguilar Contreras1, Jonathan E. Rowe2, and Christopher R. Stephens3

1Instituto de Investigación en Matemáticas Aplicadas y Sistemas,
UNAM,
Circuito Escolar,
Ciudad Universitaria, México D.F. 04510
andresac@uxmcc2.iimas.unam.mx

2School of Computer Science,
University of Birmingham,
Birmingham B15 2TT,
Great Britain
J.E.Rowe@cs.bham.ac.uk

3Instituto de Ciencias Nucleares,
UNAM,
Circuito Exterior, A.
Postal 70-543,
México D.F. 04510.
stephens@nuclecu.unam.mx

Abstract. Following the work of Stephens and coworkers on the coarse-grained dynamics of genetic systems, we work towards a possible generalisation in the context of genetic algorithms, giving as examples schemata, genotype-phenotype mappings, and error classes in the Eigen model. We discuss how the dynamics transforms under a coarse-graining, comparing and contrasting different notions of invariance. We work out some examples in the two-bit case, to illustrate the ideas and issues. We then find a bound for the Selection Weighted Linkage Disequilibrium Coefficient for the two-bit onemax problem.

LNCS 2723, p. 874 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003