摘要
提出了一种基于人工免疫系统与RBF的混合算法.该算法由两个阶段组成:第一阶段采用人工免疫机制来确定RBF网络隐层的聚类中心的位置和数量。第二阶段求输出层的权值W,最后用模式分类作试验,实验结果表明,该算法具有收敛速度快,泛化能力强的特点。
The paper presents a hybrid algorithm for artificial immune system and RBF. The algorithm includes two parts. The first part is that artificial immune system is used to determine the initial positions and number of the centers in RBF network. The second part is to calculate the matrix W. The experimental result demonstrates that this method has a fast convergence rate and good generalization ability.
出处
《韩山师范学院学报》
2007年第6期37-40,共4页
Journal of Hanshan Normal University
关键词
人工免疫系统
聚类中心
RBF
模式分类
artificial immune system
clustering centers
RBF
pattern classification
