Exponential stability analysis of neural networks with multiple time varying delays

被引:0
|
作者
Wang Zhanshan [1 ]
Mang Huaguang
机构
[1] Northeastern Univ, Sch Informat Sci & Engn, Shenyang 110004, Peoples R China
[2] Shenyang Ligong Univ, Dept Informat Engn, Shenyang 110168, Peoples R China
关键词
recurrent neural networks; multiple time delays; exponential stability; linear matrix inequality (LMI);
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Without assuming the boundedness, strict monotonicity and differentiability of the activation function, global exponential stability was investigated for a class of neural networks with multiple time varying delays. A new sufficient condition is derived to guarantee the uniqueness and global exponential stability of the equilibrium point via linear matrix inequality technique. The proposed stability criterion imposes constraints on the self-feedback matrix and interconnected matrices, which can be conveniently verified. Comparisons are made with some previous results, which shows the effectiveness of the obtained result.
引用
收藏
页码:649 / 653
页数:5
相关论文
共 50 条