Co-evolutionary global optimization algorithm

被引：0

作者：

Iwamatsu, M ^{[1
]}

机构：

[1] Kisarazu Natl Coll Technol, Dept Informat & Comp Engn, Kisarazu, Chiba 2920041, Japan

来源：

CEC'02: PROCEEDINGS OF THE 2002 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2 | 2002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：

A hybrid global optimization method, the coevolutionary global optimization algorithm, is proposed which utilizes the self-organized critical state as the mean of diversification of search and the traditional conjugate gradient local minimization method as the mean of intensification of search. The former has been recently used by Boettcher and Percus (Artificial Intelligence 119 (2000) 275) to solve discrete combinatorial optimization problems. The proposed method has been tested to locate the lowest energy conformation of atomic clusters. It was found that the method was effective not only to locate the lowest energy state but also to enumerate all the low-lying metastable states.

引用

页码：1180 / 1184

页数：5