Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
408694 | Neurocomputing | 2010 | 10 Pages |
Abstract
In this paper, the problem on global asymptotic stability analysis for a class of neural networks (NNs) with time-varying delays and general activation functions is considered. By employing a novel augmented Lyapunov–Krasoviskii functional (LKF), an improved stability condition is obtained in linear matrix inequalities form. The special cases of the obtained criterion turn out to be equivalent to some existing results but include the less number of variables. With the present stability conditions, the computational burden and conservatism are largely reduced. Examples are provided to demonstrate the advantage of the stability results.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Tao Li, Xiaoling Ye,