Adaptive Exponential Synchronization of Multislave Time-Delayed Recurrent Neural Networks With Lévy Noise and Regime Switching

Liuwei Zhou, Quanyan Zhu, Zhijie Wang, Wuneng Zhou, Hongye Su

Research output: Contribution to journalArticle

Abstract

This paper discusses the problem of adaptive exponential synchronization in mean square for a new neural network model with the following features: 1) the noise is characterized by the Lévy process and the parameters of the model change in line with the Markovian process; 2) the master system is also disturbed by the same Lévy noise; and 3) there are multiple slave systems, and the state matrix of each slave system is an affine function of the state matrices of all slave systems. Based on the Lyapunov functional theory, the generalized Itô's formula, -matrix method, and the adaptive control technique, some criteria are established to ensure the adaptive exponential synchronization in the mean square of the master system and each slave system. Moreover, the update law of the control gain and the dynamic variation of the parameters of the slave systems are provided. Finally, the effectiveness of the synchronization criteria proposed in this paper is verified by a practical example.

Original languageEnglish (US)
Pages (from-to)2885-2898
Number of pages14
JournalIEEE transactions on neural networks and learning systems
Volume28
Issue number12
DOIs
StatePublished - Dec 1 2017

Fingerprint

Recurrent neural networks
Synchronization
Gain control
Neural networks

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Adaptive Exponential Synchronization of Multislave Time-Delayed Recurrent Neural Networks With Lévy Noise and Regime Switching. / Zhou, Liuwei; Zhu, Quanyan; Wang, Zhijie; Zhou, Wuneng; Su, Hongye.

In: IEEE transactions on neural networks and learning systems, Vol. 28, No. 12, 01.12.2017, p. 2885-2898.

Research output: Contribution to journalArticle

@article{9539f9bcd37e4b8fae0ce012ab101e14,
title = "Adaptive Exponential Synchronization of Multislave Time-Delayed Recurrent Neural Networks With L{\'e}vy Noise and Regime Switching",
abstract = "This paper discusses the problem of adaptive exponential synchronization in mean square for a new neural network model with the following features: 1) the noise is characterized by the L{\'e}vy process and the parameters of the model change in line with the Markovian process; 2) the master system is also disturbed by the same L{\'e}vy noise; and 3) there are multiple slave systems, and the state matrix of each slave system is an affine function of the state matrices of all slave systems. Based on the Lyapunov functional theory, the generalized It{\^o}'s formula, -matrix method, and the adaptive control technique, some criteria are established to ensure the adaptive exponential synchronization in the mean square of the master system and each slave system. Moreover, the update law of the control gain and the dynamic variation of the parameters of the slave systems are provided. Finally, the effectiveness of the synchronization criteria proposed in this paper is verified by a practical example.",
author = "Liuwei Zhou and Quanyan Zhu and Zhijie Wang and Wuneng Zhou and Hongye Su",
year = "2017",
month = "12",
day = "1",
doi = "10.1109/TNNLS.2016.2609439",
language = "English (US)",
volume = "28",
pages = "2885--2898",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "12",

}

TY - JOUR

T1 - Adaptive Exponential Synchronization of Multislave Time-Delayed Recurrent Neural Networks With Lévy Noise and Regime Switching

AU - Zhou, Liuwei

AU - Zhu, Quanyan

AU - Wang, Zhijie

AU - Zhou, Wuneng

AU - Su, Hongye

PY - 2017/12/1

Y1 - 2017/12/1

N2 - This paper discusses the problem of adaptive exponential synchronization in mean square for a new neural network model with the following features: 1) the noise is characterized by the Lévy process and the parameters of the model change in line with the Markovian process; 2) the master system is also disturbed by the same Lévy noise; and 3) there are multiple slave systems, and the state matrix of each slave system is an affine function of the state matrices of all slave systems. Based on the Lyapunov functional theory, the generalized Itô's formula, -matrix method, and the adaptive control technique, some criteria are established to ensure the adaptive exponential synchronization in the mean square of the master system and each slave system. Moreover, the update law of the control gain and the dynamic variation of the parameters of the slave systems are provided. Finally, the effectiveness of the synchronization criteria proposed in this paper is verified by a practical example.

AB - This paper discusses the problem of adaptive exponential synchronization in mean square for a new neural network model with the following features: 1) the noise is characterized by the Lévy process and the parameters of the model change in line with the Markovian process; 2) the master system is also disturbed by the same Lévy noise; and 3) there are multiple slave systems, and the state matrix of each slave system is an affine function of the state matrices of all slave systems. Based on the Lyapunov functional theory, the generalized Itô's formula, -matrix method, and the adaptive control technique, some criteria are established to ensure the adaptive exponential synchronization in the mean square of the master system and each slave system. Moreover, the update law of the control gain and the dynamic variation of the parameters of the slave systems are provided. Finally, the effectiveness of the synchronization criteria proposed in this paper is verified by a practical example.

UR - http://www.scopus.com/inward/record.url?scp=85040704164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040704164&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2016.2609439

DO - 10.1109/TNNLS.2016.2609439

M3 - Article

C2 - 28114083

AN - SCOPUS:85040704164

VL - 28

SP - 2885

EP - 2898

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 12

ER -