Global synchronization of multiple recurrent neural networks with time delays via impulsive interactions

Shaofu Yang, Zhenyuan Guo, Jun Wang

Research output: Contribution to journalArticlepeer-review

60 Citations (Scopus)

Abstract

In this paper, new results on the global synchronization of multiple recurrent neural networks (NNs) with time delays via impulsive interactions are presented. Impulsive interaction means that a number of NNs communicate with each other at impulse instants only, while they are independent at the remaining time. The communication topology among NNs is not required to be always connected and can switch ON and OFF at different impulse instants. By using the concept of sequential connectivity and the properties of stochastic matrices, a set of sufficient conditions depending on time delays is derived to ascertain global synchronization of multiple continuous-time recurrent NNs. In addition, a counterpart on the global synchronization of multiple discrete-time NNs is also discussed. Finally, two examples are presented to illustrate the results.

Original languageEnglish
Article number7452626
Pages (from-to)1657-1667
Number of pages11
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume28
Issue number7
DOIs
Publication statusPublished - Jul 2017
Externally publishedYes

Keywords

  • Impulsive interaction
  • recurrent neural networks (NNs)
  • switching connectivity
  • synchronization

Fingerprint

Dive into the research topics of 'Global synchronization of multiple recurrent neural networks with time delays via impulsive interactions'. Together they form a unique fingerprint.

Cite this