Global Asymptotic Stability of Neural Networks With Delay: Comparative Evaluation of Two Criteria

Abstract

In [IEEE Trans Cire Syst II 2005;52(4):181-4], a criterion for the global asymptotic stability of a class of delayed neural networks has been presented. The criterion is based on the factorization B = B(1)B(2), where B denotes the delayed connection weight matrix. In the present paper, this criterion is compared with the criterion reported in [Phys Lett A 2003;311(6):504-11]. It turns out that, as far as the case of a nonsingular matrix B, is concerned, these two criteria are one and the same. (c) 2006 Elsevier Ltd. All rights reserved.