DELAY-INDEPENDENT AND DELAY-DEPENDENT STABILITY OF A NOVEL DELAYED NEURAL NETWORK

摘要

This paper is devoted to stability analysis of a novel delayed neural network, whose neurons are connected with each other through both neurons' feedback connection strength matrix and direct connection strength matrix. Both delay-independent and delay-dependent stability criteria are obtained by integrating LMI approach and Lyapunov-Krasovskii functional method By introducing some slack matrix variables, the criteria are less conservative It is the most efficient for systems with time delay The criteria are in form of LMI with more slack matrix variables, which may enlarge the range in selecting neural networks' parameters including the upper bound of delay for guaranteeing asymptotic stability of the system.