STABILITY ANALYSIS FOR A CLASS OF NEURAL NETWORKS

This paper considers the problem of characterizing the stability prope rties of the equilibria of an important class of recurrent neural netw orks. Sufficient conditions are given under which the neural network p ossesses a unique globally asymptotically stable equilibrium point for each external input. These conditions are less restrictive than those previously obtained and are easily checked, so that incorporating the m in existing neural network design procedures should increase the fle xibility and reduce the complexity of this synthesis process. Results are provided for both continuous-time and discrete time networks.