Stability Analysis of Neural-Network Large-scale Systems

Abstract

This paper is concerned with the stability problem of a neural network (NN) large-scale system which consists of a few interconnected subsystems represented by NN models. First, the dynamics of each NN model is converted into LDI (linear differential inclusion) representation. Subsequently, based on the LDI representations, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of NN large-scale systems. Finally, a numerical example with simulations is given to illustrate the results.