Publication detail

Cartesian Genetic Programming as an Optimizer of Programs Evolved with Geometric Semantic Genetic Programming

KONČAL, O. SEKANINA, L.

Original Title

Cartesian Genetic Programming as an Optimizer of Programs Evolved with Geometric Semantic Genetic Programming

Type

conference paper

Language

English

Original Abstract

In Geometric Semantic Genetic Programming (GSGP), genetic operators directly work at the level of semantics rather than syntax. It provides many advantages, including much higher quality of resulting individuals (in terms of error) in comparison with a common genetic programming. However, GSGP produces extremely huge solutions that could be difficult to apply in systems with limited resources such as embedded systems. We propose Subtree Cartesian Genetic Programming (SCGP) -- a method capable of reducing the number of nodes in the trees generated by GSGP. SCGP executes a common Cartesian Genetic Programming (CGP) on all elementary subtrees created by GSGP and on various compositions of these optimized subtrees in order to create one compact representation of the original program. SCGP does not guarantee the (exact) semantic equivalence between the CGP individuals and the GSGP subtrees, but the user can define conditions when a particular CGP individual is acceptable. We evaluated SCGP on four common symbolic regression benchmark problems and the obtained node reduction is from 92.4% to 99.9%.

Keywords

Cartesian Genetic Programming, Geometric Semantic Genetic Programming, symbolic regression, semantics 

Authors

KONČAL, O.; SEKANINA, L.

Released

21. 4. 2019

Publisher

Springer International Publishing

Location

Cham

ISBN

978-3-030-16669-4

Book

Genetic Programming 22nd European Conference, EuroGP 2019

Pages from

98

Pages to

113

Pages count

16

URL

https://www.fit.vut.cz/research/publication/11859/

BibTex

@inproceedings{BUT156847,
  author="Ondřej {Končal} and Lukáš {Sekanina}",
  title="Cartesian Genetic Programming as an Optimizer of Programs Evolved with Geometric Semantic Genetic Programming",
  booktitle="Genetic Programming 22nd European Conference, EuroGP 2019",
  year="2019",
  pages="98--113",
  publisher="Springer International Publishing",
  address="Cham",
  doi="10.1007/978-3-030-16670-0\{_}7",
  isbn="978-3-030-16669-4",
  url="https://www.fit.vut.cz/research/publication/11859/"
}