Global exponential periodicity and global exponential stability of a class of recurrent neural networks

Boshan Chen, Jun Wang

Research output: Contribution to journalArticlepeer-review

42 Citations (Scopus)

Abstract

Some sufficient criteria have been given ensuring existence, uniqueness and global exponential stability of periodic solution of a class of recurrent neural network (RNN) model by using the comparison principle, the theory of monotone flow and monotone operator. The conditions are very viable in some applied fields. For instance, they can be applied to design globally exponentially stable RNNs and periodic oscillatory RNNs and easily checked in practice. In addition, we provide a new and efficacious method for the qualitative analysis of neural networks.

Original languageEnglish
Pages (from-to)36-48
Number of pages13
JournalPhysics Letters, Section A: General, Atomic and Solid State Physics
Volume329
Issue number1-2
DOIs
Publication statusPublished - 16 Aug 2004
Externally publishedYes

Keywords

  • 85.40.Ls

Fingerprint

Dive into the research topics of 'Global exponential periodicity and global exponential stability of a class of recurrent neural networks'. Together they form a unique fingerprint.

Cite this