Order statistics and selection methods of evolutionary algorithms

被引:19
作者
Cantú-Paz, E [1 ]
机构
[1] Lawrence Livermore Natl Lab, Ctr Appl Sci Comp, Livermore, CA 94551 USA
关键词
analysis of algorithms; linear ranking; exponential ranking; tournament selection; Boltzmann selection; truncation selection; selection intensity; fitness distribution; order statistics;
D O I
10.1016/S0020-0190(01)00282-4
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Selection methods are essential components of evolutionary algorithms (EAs). This paper reviews five popular selection methods used in EAs. The algorithms are examined using the cumulants of the fitness distribution of the selected individuals. The cumulants are calculated using order statistics. The method presented here considers finite populations of arbitrary size. The results show important differences among the selection methods considered. even when they are configured to have the same selection intensity. Published by Elsevier Science B.V.
引用
收藏
页码:15 / 22
页数:8
相关论文
共 20 条
[1]  
[Anonymous], 1981, THESIS U ALBERTA EDM
[2]  
Back T., 1995, Proceedings of the 6th International Conference on Genetic Algorithms, P2
[3]  
Baker J. E., 1985, Proceedings of the International Conference on Genetic Algorithms and their Applications, P101
[4]   A ComDarison of Selection Schemes Used in Evolutionary Algorithms [J].
Blickle, Tobias ;
Thiele, Lothar .
EVOLUTIONARY COMPUTATION, 1996, 4 (04) :361-394
[5]  
Cantu-Paz E., 2000, EFFICIENT ACCURATE P
[6]  
DELAMAZA M, 1993, PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON GENETIC ALGORITHMS, P124
[7]  
Goldberg D, 1999, EVOLUTIONARY DESIGN BY COMPUTERS, P105
[8]  
Goldberg DE, 1991, FDN GENETIC ALGORITH, P69, DOI DOI 10.1016/B978-0-08-050684-5.50008-2
[9]   The Gambler's Ruin Problem, Genetic Algorithms, and the Sizing of Populations [J].
Harik, George ;
Cantu-Paz, Erick ;
Goldberg, David E. ;
Miller, Brad L. .
EVOLUTIONARY COMPUTATION, 1999, 7 (03) :231-253
[10]  
HARTER HL, 1970, ORDER STAT THEIR USE