A New Criterion for Stability of Neutral-Type Neural Networks with Discrete Delays

This paper deals with the stability problem for the class of neutral-type neural networks including discrete time delays in states and discrete neutral delays in time derivative of states. By using a generalized Lyapunov functional, a sufficient criterion is derived for the global asymptotic stability of delayed neutral-type neural networks. The proposed stability criterion is independently of the values of the time delays and neutral delays and establishes some easily verifiable algebraic mathematical relationships involving the values of the elements of the interconnection matrices and the other network parameters.