| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 410054 | Neurocomputing | 2014 | 7 Pages |
Abstract
In this paper, we investigate exponential stability of delayed recurrent neural networks. By using the delay partitioning method, some sufficient conditions are established to guarantee exponential stability of delayed recurrent neural networks under two different conditions with constructing new Lyapunov–Krasvoskii functional. This partitioning approach can reduce the conservatism comparing with some previous results of stability. At last, numerical examples are given out to show the effectiveness and advantage of our results.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Jian Xiao, Zhigang Zeng, Ailong Wu,