Detail publikace

Efficient Phenotype Evaluation in Cartesian Genetic Programming

Originální název

Efficient Phenotype Evaluation in Cartesian Genetic Programming

Anglický název

Efficient Phenotype Evaluation in Cartesian Genetic Programming

Jazyk

en

Originální abstrakt

This paper describes an efficient acceleration technique designed to speedup the evaluation of candidate solutions in Cartesian Genetic Programming (CGP). The method is based on translation of the CGP phenotype to a binary machine code that is consequently executed. The key feature of the presented approach is that the introduction of the translation mechanism into common fitness evaluation procedure requires only marginal knowledge of target CPU instruction set. The proposed acceleration technique is evaluated using a symbolic regression problem in floating point domain. It is shown that for a cost of small changes in a common CGP implementation, a significant speedup can be obtained even on a common desktop CPU.

Anglický abstrakt

This paper describes an efficient acceleration technique designed to speedup the evaluation of candidate solutions in Cartesian Genetic Programming (CGP). The method is based on translation of the CGP phenotype to a binary machine code that is consequently executed. The key feature of the presented approach is that the introduction of the translation mechanism into common fitness evaluation procedure requires only marginal knowledge of target CPU instruction set. The proposed acceleration technique is evaluated using a symbolic regression problem in floating point domain. It is shown that for a cost of small changes in a common CGP implementation, a significant speedup can be obtained even on a common desktop CPU.

BibTex


@inproceedings{BUT96987,
  author="Zdeněk {Vašíček} and Karel {Slaný}",
  title="Efficient Phenotype Evaluation in Cartesian Genetic Programming",
  annote="This paper describes an efficient acceleration technique designed to speedup the
evaluation of candidate solutions in Cartesian Genetic Programming (CGP). The
method is based on translation of the CGP phenotype to a binary machine code that
is consequently executed. The key feature of the presented approach is that the
introduction of the translation mechanism into common fitness evaluation
procedure requires only marginal knowledge of target CPU instruction set. The
proposed acceleration technique is evaluated using a symbolic regression problem
in floating point domain. It is shown that for a cost of small changes in a
common CGP implementation, a significant speedup can be obtained even on a common
desktop CPU.",
  address="Springer Verlag",
  booktitle="Proc. of the 15th European Conference on Genetic Programming",
  chapter="96987",
  doi="10.1007/978-3-642-29139-5_23",
  edition="Lecture Notes in Computer Science",
  howpublished="online",
  institution="Springer Verlag",
  year="2012",
  month="january",
  pages="266--278",
  publisher="Springer Verlag",
  type="conference paper"
}