New conditions for global exponential stability of continuous-time neural networks with delays

In this paper, we investigate the global exponential stability of delayed neural network systems. For this purpose, the activation functions are assumed to be globally Lipschitz continuous. The properties of norms and the relationship of homeomorphism are adjusted to ensure the existence as well as the uniqueness of the equilibrium point. Then by employing suitable Lyapunov functional, some delay-independent sufficient conditions are derived for exponential convergence toward global equilibrium state associated with different input sources. The obtained results are shown to be more general and less restrictive than the previous results derived in the literature. Lastly, a number of examples are provided to demonstrate the validity of the results proposed.