Compressed linear genetic programming: empirical parameter study on the Even-n-parity problem

Authors:
Johan Parent;Ann Nowé;Anne Defaweux
Affiliations:
Vrije Universiteit Brussel, Applied Science Faculty, ETRO, Brussel, Belgium;Vrije Universiteit Brussel, Faculty of Science, COMO, Brussel, Belgium;Vrije Universiteit Brussel, Faculty of Science, COMO, Brussel, Belgium
Venue:
EC'05 Proceedings of the 6th WSEAS international conference on Evolutionary computing
Year:
2005

Citing 4
Cited 0

Coevolving functions in genetic programming

Journal of Systems Architecture: the EUROMICRO Journal - Special issue on evolutionary computing
Evolving Modules in Genetic Programming by Subtree Encapsulation

EuroGP '01 Proceedings of the 4th European Conference on Genetic Programming
Proceedings of the 1st annual conference on Genetic and evolutionary computation

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
High-performance, parallel, stack-based genetic programming

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a parameter study of our Compressed Linear Genetic Programming (cl-GP) using the Even-n-parity problem. A cl-GP system is a linear genetic programming (GP) which uses substring compression as a modularization scheme. Despite the fact that the compression of substrings assumes a tight linkage between alleles, this approach improves the search process. The compression of the genotype, which is a form of linkage learning, provides both a protection mechanism and a form of genetic code reuse. This text presents a study of the different parameters of the cl-GP on Even-n-parity. Experiments indicate that the cl-GP performs best when compressing a small fraction of the population and the length of the substituted substrings is rather short.