New necessary and sufficient conditions for absolute stability of neural networks

被引:0
|
作者
Chu, TG [1 ]
Zhang, CS [1 ]
机构
[1] Peking Univ, Dept Engn Sci & Mech, Ctr Syst & Control, Beijing 100871, Peoples R China
关键词
absolute stability; global asymptotic stability; neural networks; solvable Lie algebra condition;
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
This paper presents new necessary and sufficient conditions for absolute stability of neural networks. The main result is based on a solvable Lie algebra condition, which generalizes existing results for symmetric and normal neural networks. It also demonstrates how to generate larger sets of weight matrices for absolute stability of the neural networks from known normal weight matrices through simple procedures. The approach is nontrivial in the sense that it is applicable to a class of neural networks with non-normal weight matrices.
引用
收藏
页码:593 / 598
页数:6
相关论文
共 50 条