Robust passivity analysis for discrete-time recurrent neural networks with mixed delays

Chuan Kuei Huang, Yu Jeng Shu, Koan Yuh Chang, Ho Nien Shou, Chien Yu Lu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This article considers the robust passivity analysis for a class of discrete-time recurrent neural networks (DRNNs) with mixed time-delays and uncertain parameters. The mixed time-delays that consist of both the discrete time-varying and distributed time-delays in a given range are presented, and the uncertain parameters are norm-bounded. The activation functions are assumed to be globally Lipschitz continuous. Based on new bounding technique and appropriate type of Lyapunov functional, a sufficient condition is investigated to guarantee the existence of the desired robust passivity condition for the DRNNs, which can be derived in terms of a family of linear matrix inequality (LMI). Some free-weighting matrices are introduced to reduce the conservatism of the criterion by using the bounding technique. A numerical example is given to illustrate the effectiveness and applicability.

Original languageEnglish
Pages (from-to)216-232
Number of pages17
JournalInternational Journal of Electronics
Volume102
Issue number2
DOIs
Publication statusPublished - 2015 Feb 1

Fingerprint

Recurrent neural networks
Time delay
Linear matrix inequalities
Chemical activation

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

@article{6e06e19646994c7c904e9efc1c439c49,
title = "Robust passivity analysis for discrete-time recurrent neural networks with mixed delays",
abstract = "This article considers the robust passivity analysis for a class of discrete-time recurrent neural networks (DRNNs) with mixed time-delays and uncertain parameters. The mixed time-delays that consist of both the discrete time-varying and distributed time-delays in a given range are presented, and the uncertain parameters are norm-bounded. The activation functions are assumed to be globally Lipschitz continuous. Based on new bounding technique and appropriate type of Lyapunov functional, a sufficient condition is investigated to guarantee the existence of the desired robust passivity condition for the DRNNs, which can be derived in terms of a family of linear matrix inequality (LMI). Some free-weighting matrices are introduced to reduce the conservatism of the criterion by using the bounding technique. A numerical example is given to illustrate the effectiveness and applicability.",
author = "Huang, {Chuan Kuei} and Shu, {Yu Jeng} and Chang, {Koan Yuh} and Shou, {Ho Nien} and Lu, {Chien Yu}",
year = "2015",
month = "2",
day = "1",
doi = "10.1080/00207217.2014.896043",
language = "English",
volume = "102",
pages = "216--232",
journal = "International Journal of Electronics",
issn = "0020-7217",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

Robust passivity analysis for discrete-time recurrent neural networks with mixed delays. / Huang, Chuan Kuei; Shu, Yu Jeng; Chang, Koan Yuh; Shou, Ho Nien; Lu, Chien Yu.

In: International Journal of Electronics, Vol. 102, No. 2, 01.02.2015, p. 216-232.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust passivity analysis for discrete-time recurrent neural networks with mixed delays

AU - Huang, Chuan Kuei

AU - Shu, Yu Jeng

AU - Chang, Koan Yuh

AU - Shou, Ho Nien

AU - Lu, Chien Yu

PY - 2015/2/1

Y1 - 2015/2/1

N2 - This article considers the robust passivity analysis for a class of discrete-time recurrent neural networks (DRNNs) with mixed time-delays and uncertain parameters. The mixed time-delays that consist of both the discrete time-varying and distributed time-delays in a given range are presented, and the uncertain parameters are norm-bounded. The activation functions are assumed to be globally Lipschitz continuous. Based on new bounding technique and appropriate type of Lyapunov functional, a sufficient condition is investigated to guarantee the existence of the desired robust passivity condition for the DRNNs, which can be derived in terms of a family of linear matrix inequality (LMI). Some free-weighting matrices are introduced to reduce the conservatism of the criterion by using the bounding technique. A numerical example is given to illustrate the effectiveness and applicability.

AB - This article considers the robust passivity analysis for a class of discrete-time recurrent neural networks (DRNNs) with mixed time-delays and uncertain parameters. The mixed time-delays that consist of both the discrete time-varying and distributed time-delays in a given range are presented, and the uncertain parameters are norm-bounded. The activation functions are assumed to be globally Lipschitz continuous. Based on new bounding technique and appropriate type of Lyapunov functional, a sufficient condition is investigated to guarantee the existence of the desired robust passivity condition for the DRNNs, which can be derived in terms of a family of linear matrix inequality (LMI). Some free-weighting matrices are introduced to reduce the conservatism of the criterion by using the bounding technique. A numerical example is given to illustrate the effectiveness and applicability.

UR - http://www.scopus.com/inward/record.url?scp=84911452751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911452751&partnerID=8YFLogxK

U2 - 10.1080/00207217.2014.896043

DO - 10.1080/00207217.2014.896043

M3 - Article

AN - SCOPUS:84911452751

VL - 102

SP - 216

EP - 232

JO - International Journal of Electronics

JF - International Journal of Electronics

SN - 0020-7217

IS - 2

ER -