Stabilization role of inhibitory self-connections in a delayed neural network

In a delayed Hopfield neural network that is strongly connected with non-in hibitory interconnections, fast and inhibitory self-connections lead to glo bal convergence to a unique equilibrium of the network. By applying monoton e dynamical systems theory and an embedding technique, we prove that this c onclusion remains true without the requirement of strong connectivity or no n-inhibitory interconnections. (C) 2001 Elsevier Science B.V, All rights re served.