Global asymptotic and exponential stability of a dynamic neural system with asymmetric connection weights

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

41 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)635-638
Journal / PublicationIEEE Transactions on Automatic Control
Volume46
Issue number4
Publication statusPublished - Apr 2001
Externally publishedYes

Abstract

Recently, a dynamic neural system was presented and analyzed due to its good performance in optimization computation and low complexity for implementation. The global asymptotic stability of such a dynamic neural system with symmetric connection weights was well studied. In this note, based on a new Lyapunov function, we investigate the global asymptotic stability of the dynamic neural system with asymmetric connection weights. Since the dynamic neural system with asymmetric weights is more general than that with symmetric ones, the new results are significant in both theory and applications. Specially, the new result can cover the asymptotic stability results of linear systems as special cases.

Research Area(s)

  • Asymmetric connection weights, Global asymptotic stability, Neural networks