Noise-induced stabilization of the recurrent neural networks with mixed time-varying delays and Markovian-switching parameters

Yi Shen, Jun Wang

Research output: Contribution to journalArticlepeer-review

82 Citations (Scopus)

Abstract

The stabilization of recurrent neural networks with mixed time-varying delays and Markovian-switching parameters by noise is discussed. First, a new result is given for the existence of unique states of recurrent neural networks (NNs) with mixed time-varying delays and Markovian-switching parameters in the presence of noise, without the need to satisfy the linear growth conditions required by general stochastic Markovian-switching systems. Next, a delay-dependent condition for stabilization of concerned recurrent NNs is derived by applying the Itô formula, the Gronwall inequality, the law of large numbers, and the ergodic property of Markovian chain. The results show that there always exists an appropriate white noise such that any recurrent NNs with mixed time-varying delays and Markovian-switching parameters can be exponentially stabilized by noise if the delays are sufficiently small.

Original languageEnglish
Pages (from-to)1857-1862
Number of pages6
JournalIEEE Transactions on Neural Networks
Volume18
Issue number6
DOIs
Publication statusPublished - Nov 2007
Externally publishedYes

Keywords

  • Markovian chain
  • Noise
  • Recurrent neural networks (NNs)
  • Stabilization
  • Time-varying delay

Fingerprint

Dive into the research topics of 'Noise-induced stabilization of the recurrent neural networks with mixed time-varying delays and Markovian-switching parameters'. Together they form a unique fingerprint.

Cite this