Global robust stability of a class of discrete-time interval neural networks

Sanqing Hu, Jun Wang

Research output: Contribution to journalArticlepeer-review

59 Citations (Scopus)

Abstract

This paper is concerned with global robust stability of a general class of discrete-time interval neural networks which contain time-invariant uncertain parameters with their values being unknown but bounded in given compact sets. We first introduce the concept of diagonally constrained interval neural networks and present a necessary and sufficient condition for global robust stability of the interval networks regardless of the bounds of nondiagonal uncertain parameters of state feedback and connection weight matrices. Then we extend the result to general interval neural networks. Finally, simulation results illustrate the characteristics of the main results.

Original languageEnglish
Pages (from-to)129-138
Number of pages10
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Volume53
Issue number1
DOIs
Publication statusPublished - Jan 2006
Externally publishedYes

Keywords

  • Discrete-time
  • Global robust stable
  • Interval matrix
  • Neural network

Fingerprint

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

Cite this