Global Robust Stability of Interval Delayed Neural Networks

Abstract

In recent years, the problem of global robust stability of Hopfield-type interval delayed neural networks has received considerable attention. A number of criteria for the global robust stability of such networks have been reported in the literature. On the basis of the idea of dividing (in respect of both the connection weight matrix A and the delayed connection weight matrix B) the given interval into two intervals, four new criteria for the global robust stability of such networks are established. The criteria are in the form of linear matrix inequality and, hence, computationally tractable. The criteria yield a less conservative condition compared with many recently reported criteria, as is demonstrated with an example.