An analysis of global robust stability of delayed dynamical neural networks

This paper studies the problem of establishing robust asymptotic stability of neural networks with multiple time delays and in the presence of the parameter uncertainties of the network. A new sufficient condition ensuring robust asymptotic stability is presented by manipulating the properties of some certain classes of real matrices and employing Homomorphic mapping and Lyapunov stability theorems. A numerical example is given to show that the condition obtained can outperform alternative ones in terms of conservatism and computational complexity.