A New Lyapunov Analysis of Robust Stability of Neural Networks with Discrete Time Delays.

This paper studies the global asymptotic robust stability of dynamical neural networks with discrete time delays under parameter uncertainties. By utilising the Lyapunov stability and Homeomorphic mapping theorems, a new sufficient condition is presented for the existence, uniqueness and global robust asymptotic stability of this class of neural systems with respect to the Lipschitz continuous activation functions. The proposed stability criterion is derived by employing a new type of Lyapunov functional and it unifies some of the key robust stability results obtained in the past literature.