Theoretical analysis of evolutionary algorithms with an infinite population size in continuous space. Part II: Analysis of the diversification role of crossover

Author

Qi, Xiaofeng ; Palmieri, Francesco

Author_Institution

Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT, USA

Volume

5

Issue

1

fYear

1994

fDate

1/1/1994 12:00:00 AM

Firstpage

120

Lastpage

129

Abstract

For pt. I see ibid., p. 102-19. In this part of the paper the authors concentrate on the unique diversification role of the crossover operator in genetic algorithms. The explorative behavior of a generic crossover operator is revealed through a detailed large-sample analysis. Recursive equations for the population distributions are derived for a uniform crossover operator in multi-dimensional continuous space, showing how the crossover operator probes new regions of the solution space while keeping the population within the feasible region. The results of this analysis can be extended to the setting of a discrete space in a straightforward manner, shedding much light on the understanding of the essential role of crossover in genetic algorithms

Keywords

genetic algorithms; optimisation; statistical analysis; continuous space; crossover; discrete space; diversification role; evolutionary algorithms; genetic algorithms; infinite population size; large-sample analysis; multi-dimensional continuous space; population distributions; recursive equations; Algorithm design and analysis; Biological cells; Biology computing; Equations; Evolutionary computation; Genetic algorithms; Genetic mutations; Predictive models; Probes; Systems engineering and theory;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.265966

Filename

265966