Global stability of a class of discrete-time recurrent neural networks

Sanqing Hu, Jun Wang

Research output: Contribution to journalArticlepeer-review

55 Citations (Scopus)


This paper presents several analytical results on global asymptotic stability (GAS) and global exponential stability (GES) for the equilibrium states of a general class of discrete-time recurrent neural networks (DTRNNS) with asymmetric connection weight matrices and globally Lipschitz continuous and monotone nondecreasing activation functions. A necessary and sufficient condition is formulated to guarantee the existence and uniqueness of equilibria of such DTRNNS. The obtained results are less restrictive, different from, and improve upon the existing ones on GAS and GES of neural networks with special classes of activation functions.

Original languageEnglish
Pages (from-to)1104-1117
Number of pages14
JournalIEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
Issue number8
Publication statusPublished - Aug 2002
Externally publishedYes


  • Discrete-time
  • Global asymptotic stability
  • Global exponential stability
  • Global Lipschitz continuous
  • Recurrent neural networks


Dive into the research topics of 'Global stability of a class of discrete-time recurrent neural networks'. Together they form a unique fingerprint.

Cite this