Evolution of recursive programs with multi-niche genetic programming (mnGP)

Author

Nishiguchi, Masato ; Fujimoto, Yoshiji

Author_Institution

Software Eng. Center, Hitachi Software Eng. Co. Ltd., Kanagawa, Japan

fYear

1998

fDate

4-9 May 1998

Firstpage

247

Lastpage

252

Abstract

A recursive program is one of the most intelligent and sophisticated programs written by a human programmer. This paper provides challenging experiments for the evolution of such an intelligent recursive program with genetic programming (GP). In this paper, we propose two types of multi-niche GP (mnGP): GP with structure-based multi-niches and GP with fitness case-based multi-niches. We apply them to Fibonacci series and to a search problem. We have obtained outstanding results with mnGP for these problems

Keywords

genetic algorithms; mathematics computing; programming; search problems; series (mathematics); Fibonacci series; fitness case-based multi-niches; intelligent recursive program evolution; multi-niche genetic programming; search problem; structure-based multi-niches; Biological systems; Evolution (biology); Genetic programming; Humans; Informatics; Mathematics; Programming profession; Search problems; Software engineering; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on

Conference_Location

Anchorage, AK

Print_ISBN

0-7803-4869-9

Type

conf

DOI

10.1109/ICEC.1998.699720

Filename

699720