Genetic algorithm: Difference between revisions

Revision as of 15:10, 7 August 2007

Revision as of 22:25, 9 August 2007

Line 90:

Gaussian adaptation is able to approximate the natural process by an adaptation of the moment matrix of the Gaussian. So, because very many quantitative characters are Gaussian distributed in a large population, Gaussian adaptation may serve as a genetic algorithm replacing the rules of genetic variation by a Gaussian random number generator working on the phenotypic level. See Kjellström 1996<ref>{{cite journal|last=Kjellström|first=G.|title=Evolution as a statistical optimization algorithm|journal=Evolutionary Theory|issue=11|pages=105-117|month=January|year=1996}}</ref>

[[Population-based incremental learning]] is a variation where the population as a whole is evolved rather than its individual members.

==Problem domains==