New criteria on global robust stability of Cohen–Grossberg neural networks with time-varying delays

Abstract

This paper considers the problem of robust stability analysis of Cohen–Grossberg neural networks with time-varying delays and norm-bounded parameter uncertainties. The activation functions are assumed to be bounded and globally Lipschitz continuous. Both the monotonic increasing and non-monotonic increasing activations are considered. In terms of linear matrix inequalities (LMIs), sufficient conditions are obtained by using the Lyapunov–Krasovskii method, which guarantee the existence, uniqueness and global robust asymptotic stability of the equilibrium point of the delayed Cohen–Grossberg neural network. It is theoretically established that the derived LMI conditions are less conservative than certain existing ones in the literature. Finally, numerical examples are provided to demonstrate the less conservatism and effectiveness of the proposed LMI conditions.