Optimizing genetic algorithms using self-adaptation and explored space modelization

被引：0

作者：

Martin, O ^{[1
]}

Gras, R ^{[1
]}

Hernandez, D ^{[1
]}

Appel, RD ^{[1
]}

机构：

[1] CMU, Swiss Inst Bioinformat, CH-1211 Geneva 4, Switzerland

来源：

PROCEEDINGS OF THE 7TH JOINT CONFERENCE ON INFORMATION SCIENCES | 2003年

关键词：

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 new genetic algorithm (Highway) tailored to optimize the exploration/exploitation ratio, in order to limit premature convergence (local optima). This algorithm was compared with a classical genetic algorithm and with the Bayesian Optimization Algorithm (BOA, [6]) method on common test functions. It shows an improvement over both of them.

引用

页码：291 / 294

页数：4