Stability analysis of neural networks via Lyapunov approach

This paper discusses stability of neural networks (NN) by Lyapunov approach. First, it is pointed out that the dynamic of NN systems can be represented by a class of nonlinear systems which is locally described by some different linear systems. Next, stability conditions for the class of nonlinear systems are derived and applied to stability analysis of NN systems. Finally, stability criteria of NN systems are demonstrated.