On stability of nonlinear continuous-time neural networks with delays

We utilize the Lyapunov function method to analyze stability of continuous nonlinear neural networks with delays and obtain some new sufficient condit ions ensuring the globally asymptotic stability independent of delays. Thre e main conditions imposed on the weighting matrices are established. (i). T he spectral radius rho (M-1(\W-0\ + \W-tau\)K) < 1. (ii). The row norm <par allel>M-1(\W-0\ + \W-tau\)K + P-1((\W-0\ + \W-tau\)KM-1)P-T parallel to (in finity) < 2. (iii). <mu>(2)(W-0) + parallel toW(tau)parallel to (2,F) < (m/ k). These three conditions are independent to each other. The delayed Hopfi eld network, Bidirectional associative memory network and cellular neural n etwork are special cases of the network model considered in this paper. So we improve some previous works of other researchers. (C) 2000 Elsevier Scie nce Ltd. All rights reserved.