Stability analysis of second order hopfield neural networks with time delays

  • Authors:
  • Jinan Pei;Daoyi Xu;Zhichun Yang;Wei Zhu

  • Affiliations:
  • Department of Math., Chongqing Education College, Chongqing, China;Institute of Mathematics, Sichuan University, Chengdu, China;Institute of Mathematics, Sichuan University, Chengdu, China;Institute of Mathematics, Sichuan University, Chengdu, China

  • Venue:
  • ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, some sufficient conditions of uniform stability and asymptotic stability about second order neural networks with time delays were obtained by the properties of nonnegative matrices and techniques of differential inequalities. In the results, it was assumed that the activation functions satisfy the Lipschitz condition and it was not required that the activation functions were bounded, differentiable and strictly increasing. Moreover, the symmetry of the connection matrix was not also necessary. Thus, we have improved some previous work of other researchers.