Global exponential stability for a class of generalized neural networks with distributed delays

By employing several Lyapunov functionals, the global exponential stability and asymptotic stability of generalized neural networks with distributed delays are investigated in this paper. A number of sufficient conditions for these types of stability are derived. They are milder and more general than previously known criteria, and can be applied to neural networks with constant connection weights as well as a broad range of activation functions assuming neither differentiability nor strict monotonicity. Furthermore, the results obtained for generalized neural networks with distributed delays do not assume symmetry of the connection matrix. © 2003 Published by Elsevier Ltd.