Publication Details

Adaptive Fitness Predictors in Coevolutionary Cartesian Genetic Programming

DRAHOŠOVÁ Michaela, SEKANINA Lukáš and WIGLASZ Michal. Adaptive Fitness Predictors in Coevolutionary Cartesian Genetic Programming. Evolutionary Computation, vol. 27, no. 3, 2019, pp. 497-523. ISSN 1063-6560.
Czech title
Adaptivní prediktory fitness v koevolučním kartézském genetickém programování
Type
journal article
Language
english
Authors
Keywords

Cartesian genetic programming, coevolutionary algorithms, fitness prediction, symbolic regression, evolutionary design, image processing.

Abstract

In genetic programming (GP), computer programs are often coevolved with training data subsets that are known as fitness predictors. In order to maximize performance of GP, it is important to find the most suitable parameters of coevolution, particularly the fitness predictor size. This is a very time consuming process as the predictor size depends on a given application and many experiments have to be performed to find its suitable size. A new method is proposed which enables us to automatically adapt the predictor and its size for a given problem and thus to reduce not only the time of evolution, but also the time needed to tune the evolutionary algorithm. The method was implemented in the context of Cartesian genetic programming and evaluated using five symbolic regression problems and three image filter design problems. In comparison with three different CGP implementations, the time required by CGP search was reduced while the quality of results remained unaffected.

Published
2019
Pages
497-523
Journal
Evolutionary Computation, vol. 27, no. 3, ISSN 1063-6560
Publisher
MIT Press
DOI
UT WoS
000483650900005
EID Scopus
BibTeX
@ARTICLE{FITPUB11206,
   author = "Michaela Draho\v{s}ov\'{a} and Luk\'{a}\v{s} Sekanina and Michal Wiglasz",
   title = "Adaptive Fitness Predictors in Coevolutionary Cartesian Genetic Programming",
   pages = "497--523",
   journal = "Evolutionary Computation",
   volume = 27,
   number = 3,
   year = 2019,
   ISSN = "1063-6560",
   doi = "10.1162/evco\_a\_00229",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11206"
}
Files
Back to top