Robust convergence of Cohen-Grossberg neural networks with time-varying delays
Abstract
In this paper, robust convergence is studied for the Cohen-Grossberg neural networks (CGNNs) with time-varying delays. By applying the differential inequality and the Lyapunov method, some delay-independent conditions are derived ensuring the robust CGNNs to converge, globally, uniformly and exponentially, to a ball in the state space with a pre-specified convergence rate. Finally, the effectiveness of our results are verified by an illustrative example.
- Publication:
-
Chaos Solitons and Fractals
- Pub Date:
- May 2009
- DOI:
- 10.1016/j.chaos.2007.08.072
- Bibcode:
- 2009CSF....40.1176X