Selection analysis in genetic algorithms

被引：0

作者：

Galaviz-Casas, J ^{[1
]}

机构：

[1] Univ Nacl Autonoma Mexico, Inst Matemat, Area Inv Cientif, CU, Mexico City 04510, DF, Mexico

来源：

PROGRESS IN ARTIFICIAL INTELLIGENCE-IBERAMIA 98 | 1998年 / 1484卷

关键词：

genetic algorithms; Hamming distance; partition; poset; metric space; convergence; entropy;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes a formal framework for the analysis of genetic algorithms. The model is based on the idea that over the space of populations an equivalence relation can be defined, as well as a metric on the space of equivalence classes induced by this relation. With this tools it can be proved that selection in a GA causes some kind of convergence and entropy reduction. The model is not restricted to a particular kind of selection.

引用

页码：283 / 292

页数：10