Conference paper

 
Šikulová, M., Sekanina, L.: Coevolution in Cartesian Genetic Programming, In: Proc. of the 15th European Conference on Genetic Programming, Heidelberg, DE, Springer, 2012, p. 182-193, ISBN 978-3-642-29138-8
Publication language:english
Original title:Coevolution in Cartesian Genetic Programming
Title (cs):Koevoluce v kartézském genetickém programování
Pages:182-193
Proceedings:Proc. of the 15th European Conference on Genetic Programming
Conference:15th European Conference on Genetic Programming
Series:LNCS 7244
Place:Heidelberg, DE
Year:2012
URL:http://www.springerlink.com/content/e47453258l284p60/fulltext.pdf
ISBN:978-3-642-29138-8
Publisher:Springer Verlag
URL:http://www.springerlink.com/content/e47453258l284p60/fulltext.pdf [PDF]
Files: 
+Type Name Title Size Modified
iconEuroGP2012.pdf449 KB2012-04-24 13:50:44
^ Select all
With selected:
Keywords
Cartesian genetic programming, coevolution, fitness modeling, fitness predictors, symbolic regression.

Annotation
Cartesian genetic programming (CGP) is a branch of genetic programming which has been utilized in various applications. This paper proposes to introduce coevolution to CGP in order to accelerate the task of symbolic regression. In particular, fitness predictors which are small subsets of the training set are coevolved with CGP programs. It is shown using five symbolic regression problems that the (median) execution time can be reduced 2-5 times in comparison with the standard CGP.

BibTeX:
@INPROCEEDINGS{
   author = {Michaela Šikulová and Lukáš Sekanina},
   title = {Coevolution in Cartesian Genetic Programming},
   pages = {182--193},
   booktitle = {Proc. of the 15th European Conference on Genetic Programming},
   series = {LNCS 7244},
   year = {2012},
   location = {Heidelberg, DE},
   publisher = {Springer Verlag},
   ISBN = {978-3-642-29138-8},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9832}
}