Improved exponential stability analysis for delayed recurrent neural networks

Magdi S. Mahmoud; Yuanqing Xia

doi:10.1016/j.jfranklin.2010.11.002

Improved exponential stability analysis for delayed recurrent neural networks

Magdi S. Mahmoud, Yuanqing Xia

Research output: Contribution to journal › Article › peer-review

46 Scopus citations

Abstract

In this paper, we investigate the problem of global exponential stability analysis for a class of delayed recurrent neural networks. This class includes Hopfield neural networks and cellular neural networks with interval time-delays. Improved exponential stability condition is derived by employing new LyapunovKrasovskii functional and the integral inequality. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are less conservative than previous published ones in the literature, which are illustrated by representative numerical examples.

Original language	English
Pages (from-to)	201-211
Number of pages	11
Journal	Journal of the Franklin Institute
Volume	348
Issue number	2
DOIs	https://doi.org/10.1016/j.jfranklin.2010.11.002
State	Published - Mar 2011

Bibliographical note

Funding Information:
The first author would like to thank the deanship for scientific research (DSR) at KFUPM for support through research project IN010018 .

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications
Applied Mathematics

Access to Document

10.1016/j.jfranklin.2010.11.002

Cite this

@article{ff3a9513e6284b9888b224b8dab67736,

title = "Improved exponential stability analysis for delayed recurrent neural networks",

abstract = "In this paper, we investigate the problem of global exponential stability analysis for a class of delayed recurrent neural networks. This class includes Hopfield neural networks and cellular neural networks with interval time-delays. Improved exponential stability condition is derived by employing new LyapunovKrasovskii functional and the integral inequality. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are less conservative than previous published ones in the literature, which are illustrated by representative numerical examples.",

author = "Mahmoud, \{Magdi S.\} and Yuanqing Xia",

note = "Funding Information: The first author would like to thank the deanship for scientific research (DSR) at KFUPM for support through research project IN010018 .",

year = "2011",

month = mar,

doi = "10.1016/j.jfranklin.2010.11.002",

language = "English",

volume = "348",

pages = "201--211",

journal = "Journal of the Franklin Institute",

issn = "0016-0032",

number = "2",

}

TY - JOUR

T1 - Improved exponential stability analysis for delayed recurrent neural networks

AU - Mahmoud, Magdi S.

AU - Xia, Yuanqing

N1 - Funding Information: The first author would like to thank the deanship for scientific research (DSR) at KFUPM for support through research project IN010018 .

PY - 2011/3

Y1 - 2011/3

N2 - In this paper, we investigate the problem of global exponential stability analysis for a class of delayed recurrent neural networks. This class includes Hopfield neural networks and cellular neural networks with interval time-delays. Improved exponential stability condition is derived by employing new LyapunovKrasovskii functional and the integral inequality. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are less conservative than previous published ones in the literature, which are illustrated by representative numerical examples.

AB - In this paper, we investigate the problem of global exponential stability analysis for a class of delayed recurrent neural networks. This class includes Hopfield neural networks and cellular neural networks with interval time-delays. Improved exponential stability condition is derived by employing new LyapunovKrasovskii functional and the integral inequality. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are less conservative than previous published ones in the literature, which are illustrated by representative numerical examples.

UR - https://www.scopus.com/pages/publications/79251601212

U2 - 10.1016/j.jfranklin.2010.11.002

DO - 10.1016/j.jfranklin.2010.11.002

M3 - Article

AN - SCOPUS:79251601212

SN - 0016-0032

VL - 348

SP - 201

EP - 211

JO - Journal of the Franklin Institute

JF - Journal of the Franklin Institute

IS - 2

ER -

Improved exponential stability analysis for delayed recurrent neural networks

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this