A new condition for robust stability of uncertain neural networks with time delays

This paper is concerned with the global asymptotic stability problem of dynamical neural networks with multiple time delays under parameter uncertainties. First carrying out an analysis of existence and uniqueness of the equilibrium point by means of the Homeomorphism theory, and then, studying the global asymptotic stability of the equilibrium point by constructing a suitable Lyapunov functional, we derive a new global robust stability criterion for the class of delayed neural networks with respect to the Lipschitz activation functions. The result obtained establishes a relationship between the neural network parameters only and it is independent of the time delay parameters. It is shown that the established stability condition generalizes some existing ones and it can be considered to an alternative result to some other corresponding results derived in previous literature. We also give some comparative numerical examples to demonstrate the validity and effectiveness of our proposed result.