Discrete-time bidirectional associative memory neural networks with variable delays

Jinling Liang; Jinde Cao; Daniel W.C. Ho

doi:10.1016/j.physleta.2004.12.026

Discrete-time bidirectional associative memory neural networks with variable delays

Jinling Liang, Jinde Cao, Daniel W.C. Ho

Department of Mathematics

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

107 Citations (Scopus)

Abstract

Based on the linear matrix inequality (LMI), some sufficient conditions are presented in this Letter for the existence, uniqueness and global exponential stability of the equilibrium point of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Some of the stability criteria obtained in this Letter are delay-dependent, and some of them are delay-independent, they are less conservative than the ones reported so far in the literature. Furthermore, the results provide one more set of easily verified criteria for determining the exponential stability of discrete-time BAM neural networks. © 2004 Elsevier B.V. All rights reserved.

Original language	English
Pages (from-to)	226-234
Journal	Physics Letters, Section A: General, Atomic and Solid State Physics
Volume	335
Issue number	2-3
DOIs	https://doi.org/10.1016/j.physleta.2004.12.026
Publication status	Published - 7 Feb 2005

Research Keywords

Bidirectional associative memory (BAM)
Discrete-time
Global exponential stability
Linear matrix inequality (LMI)
Lyapunov functionals
Neural networks

Access Output

10.1016/j.physleta.2004.12.026

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{f3ae807ebf0b46cc9040fd82b6fc6163,

title = "Discrete-time bidirectional associative memory neural networks with variable delays",

abstract = "Based on the linear matrix inequality (LMI), some sufficient conditions are presented in this Letter for the existence, uniqueness and global exponential stability of the equilibrium point of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Some of the stability criteria obtained in this Letter are delay-dependent, and some of them are delay-independent, they are less conservative than the ones reported so far in the literature. Furthermore, the results provide one more set of easily verified criteria for determining the exponential stability of discrete-time BAM neural networks. {\textcopyright} 2004 Elsevier B.V. All rights reserved.",

keywords = "Bidirectional associative memory (BAM), Discrete-time, Global exponential stability, Linear matrix inequality (LMI), Lyapunov functionals, Neural networks",

author = "Jinling Liang and Jinde Cao and Ho, {Daniel W.C.}",

year = "2005",

month = feb,

day = "7",

doi = "10.1016/j.physleta.2004.12.026",

language = "English",

volume = "335",

pages = "226--234",

journal = "Physics Letters, Section A: General, Atomic and Solid State Physics",

issn = "0375-9601",

publisher = "Elsevier B.V.",

number = "2-3",

}

TY - JOUR

T1 - Discrete-time bidirectional associative memory neural networks with variable delays

AU - Liang, Jinling

AU - Cao, Jinde

AU - Ho, Daniel W.C.

PY - 2005/2/7

Y1 - 2005/2/7

N2 - Based on the linear matrix inequality (LMI), some sufficient conditions are presented in this Letter for the existence, uniqueness and global exponential stability of the equilibrium point of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Some of the stability criteria obtained in this Letter are delay-dependent, and some of them are delay-independent, they are less conservative than the ones reported so far in the literature. Furthermore, the results provide one more set of easily verified criteria for determining the exponential stability of discrete-time BAM neural networks. © 2004 Elsevier B.V. All rights reserved.

AB - Based on the linear matrix inequality (LMI), some sufficient conditions are presented in this Letter for the existence, uniqueness and global exponential stability of the equilibrium point of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Some of the stability criteria obtained in this Letter are delay-dependent, and some of them are delay-independent, they are less conservative than the ones reported so far in the literature. Furthermore, the results provide one more set of easily verified criteria for determining the exponential stability of discrete-time BAM neural networks. © 2004 Elsevier B.V. All rights reserved.

KW - Bidirectional associative memory (BAM)

KW - Discrete-time

KW - Global exponential stability

KW - Linear matrix inequality (LMI)

KW - Lyapunov functionals

KW - Neural networks

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-12544259222&origin=recordpage

UR - http://www.scopus.com/inward/record.url?scp=12544259222&partnerID=8YFLogxK

U2 - 10.1016/j.physleta.2004.12.026

DO - 10.1016/j.physleta.2004.12.026

M3 - RGC 21 - Publication in refereed journal

SN - 0375-9601

VL - 335

SP - 226

EP - 234

JO - Physics Letters, Section A: General, Atomic and Solid State Physics

JF - Physics Letters, Section A: General, Atomic and Solid State Physics

IS - 2-3

ER -

Discrete-time bidirectional associative memory neural networks with variable delays

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this