LMI-based exponential stability criterion for bidirectional associative memory neural networks

Magdi S. Mahmoud; Yuanqing Xia

doi:10.1016/j.neucom.2010.03.006

LMI-based exponential stability criterion for bidirectional associative memory neural networks

Magdi S. Mahmoud^*, Yuanqing Xia

^*Corresponding author for this work

School of Automation

King Fahd University of Petroleum and Minerals

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

22 Citations (Scopus)

Abstract

In this paper, we investigate the problem of global exponential stability analysis for a class of bidirectional associative memory (BAM) neural networks with interval time-delays. Improved exponential stability condition is derived by employing new Lyapunov-Krasovskii functional and the integral inequality. Several special cases of interest are derived. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are shown to be less conservative than previous published ones in the literature. Finally, simulations of two numerical examples are provided to demonstrate the efficacy of our approach.

Original language	English
Pages (from-to)	284-290
Number of pages	7
Journal	Neurocomputing
Volume	74
Issue number	1-3
DOIs	https://doi.org/10.1016/j.neucom.2010.03.006
Publication status	Published - Dec 2010

Keywords

BAM neural networks
Global exponential stability
Interval time-delays
LMIs

Access to Document

10.1016/j.neucom.2010.03.006

Cite this

@article{66fbf84b1c23451b9839987be649a5bb,

title = "LMI-based exponential stability criterion for bidirectional associative memory neural networks",

abstract = "In this paper, we investigate the problem of global exponential stability analysis for a class of bidirectional associative memory (BAM) neural networks with interval time-delays. Improved exponential stability condition is derived by employing new Lyapunov-Krasovskii functional and the integral inequality. Several special cases of interest are derived. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are shown to be less conservative than previous published ones in the literature. Finally, simulations of two numerical examples are provided to demonstrate the efficacy of our approach.",

keywords = "BAM neural networks, Global exponential stability, Interval time-delays, LMIs",

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

year = "2010",

month = dec,

doi = "10.1016/j.neucom.2010.03.006",

language = "English",

volume = "74",

pages = "284--290",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

number = "1-3",

}

TY - JOUR

T1 - LMI-based exponential stability criterion for bidirectional associative memory neural networks

AU - Mahmoud, Magdi S.

AU - Xia, Yuanqing

PY - 2010/12

Y1 - 2010/12

N2 - In this paper, we investigate the problem of global exponential stability analysis for a class of bidirectional associative memory (BAM) neural networks with interval time-delays. Improved exponential stability condition is derived by employing new Lyapunov-Krasovskii functional and the integral inequality. Several special cases of interest are derived. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are shown to be less conservative than previous published ones in the literature. Finally, simulations of two numerical examples are provided to demonstrate the efficacy of our approach.

AB - In this paper, we investigate the problem of global exponential stability analysis for a class of bidirectional associative memory (BAM) neural networks with interval time-delays. Improved exponential stability condition is derived by employing new Lyapunov-Krasovskii functional and the integral inequality. Several special cases of interest are derived. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are shown to be less conservative than previous published ones in the literature. Finally, simulations of two numerical examples are provided to demonstrate the efficacy of our approach.

KW - BAM neural networks

KW - Global exponential stability

KW - Interval time-delays

KW - LMIs

UR - http://www.scopus.com/inward/record.url?scp=78649461881&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2010.03.006

DO - 10.1016/j.neucom.2010.03.006

M3 - Article

AN - SCOPUS:78649461881

SN - 0925-2312

VL - 74

SP - 284

EP - 290

JO - Neurocomputing

JF - Neurocomputing

IS - 1-3

ER -

LMI-based exponential stability criterion for bidirectional associative memory neural networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this