摘要
基于生物免疫学抗体克隆选择学说,本文探讨了免疫克隆选择算法(Immune Clonal Selection Algorithm,ICSA)的网络拓扑结构,然后基于李亚普洛夫稳定性定理,分析了算法的动态特性,并构造了一种基于伪梯度的混合免疫克隆网络算法,相应函数优化的试验表明,增加基于伪梯度的搜索后,在一定程度上对ICSA的性能有较大改善。
Based on immunological antibody clonal selection theory, the general steps of Immune Clonal Selection Algorithm (ICSA) are presented in this paper. We put forward the network framework of ICSA, and the dynamic characteristics of ICSA based on the Lyapunov theory are analyzed. Then this paper introuduces a novel Artificial Immune System Algorithm, Pseudo--Grads Hybrid Immune Clonal Selection Network (GHICSN). The simulation results of some functions optimization indicate that GHlCSN improves the performance of ICSA to some extend.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2005年第2期198-204,共7页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金(No.60133010
60372045)
国家重点基础研究发展计划973(No.2001CB309403)资助项目
