Convergence of MEC in bounded and continuous search space

被引：0
|
作者：
Zhou, XL [1 ]
Sun, CY [1 ]
机构：
[1] Beijing City Coll, AI Inst, Beijing 100083, Peoples R China
来源：
2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7 | 2004年
关键词：
evolutionary computation; mind evolutionary computation; Markov chain; convergence; operation similartaxis; operation dissimilation;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Mind Evolutionary Computation (MEC) is a new approach of Evolutionary Computation (EC) proposed by Chengyi Sun in 1998. The proposal is based on the study of the problems of GA and on the analysis of human mind progress. MEC comprises two kinds of operations --similartaxis and dissimilation. In this paper the operations similartaxis and dissimilation are theoretically described in detail. The wrong theorem in [13] is pointed out in this paper. It is proved that the scatter center sequence of each group generated through similartaxis iteration converges in probability to local optimal state set. Estimation of upper bound of the convergence rate is given. It is finally proved that the sequence of mature groups generated through operations similartaxis and dissimilation converges in probability to global optimal set.
引用
收藏
页码：1412 / 1419
页数：8
相关论文
共 50 条
12345