A new stability criterion for discrete-time neural networks: Nonlinear spectral radius

K. L. Mak; J. G. Peng; Z. B. Xu; Ka Fai Cedric Yiu

doi:10.1016/j.chaos.2005.09.075

A new stability criterion for discrete-time neural networks: Nonlinear spectral radius

K. L. Mak, J. G. Peng, Z. B. Xu, Ka Fai Cedric Yiu

Research output: Journal article publication › Journal article › Academic research › peer-review

16 Citations (Scopus)

Abstract

In this paper, the exponential stability of nonlinear discrete-time systems is studied. A novel notion of nonlinear spectral radius is defined. Under the assumption of Lipschitz continuity for the activation function, the developed approach is applied to stability analysis of discrete-time neural networks. A series of sufficient conditions for global exponential stability of the neural networks are established and an estimate of the exponential decay rate is also derived for each case.

Original language	English
Pages (from-to)	424-436
Number of pages	13
Journal	Chaos, Solitons and Fractals
Volume	31
Issue number	2
DOIs	https://doi.org/10.1016/j.chaos.2005.09.075
Publication status	Published - 1 Jan 2007
Externally published	Yes

ASJC Scopus subject areas

Statistical and Nonlinear Physics

More information

10.1016/j.chaos.2005.09.075

Cite this

@article{30ebd64bded5469aa7d0ab904189c228,

title = "A new stability criterion for discrete-time neural networks: Nonlinear spectral radius",

abstract = "In this paper, the exponential stability of nonlinear discrete-time systems is studied. A novel notion of nonlinear spectral radius is defined. Under the assumption of Lipschitz continuity for the activation function, the developed approach is applied to stability analysis of discrete-time neural networks. A series of sufficient conditions for global exponential stability of the neural networks are established and an estimate of the exponential decay rate is also derived for each case.",

author = "Mak, {K. L.} and Peng, {J. G.} and Xu, {Z. B.} and Yiu, {Ka Fai Cedric}",

year = "2007",

month = jan,

day = "1",

doi = "10.1016/j.chaos.2005.09.075",

language = "English",

volume = "31",

pages = "424--436",

journal = "Chaos, Solitons and Fractals",

issn = "0960-0779",

publisher = "Elsevier Ltd",

number = "2",

}

TY - JOUR

T1 - A new stability criterion for discrete-time neural networks: Nonlinear spectral radius

AU - Mak, K. L.

AU - Peng, J. G.

AU - Xu, Z. B.

AU - Yiu, Ka Fai Cedric

PY - 2007/1/1

Y1 - 2007/1/1

N2 - In this paper, the exponential stability of nonlinear discrete-time systems is studied. A novel notion of nonlinear spectral radius is defined. Under the assumption of Lipschitz continuity for the activation function, the developed approach is applied to stability analysis of discrete-time neural networks. A series of sufficient conditions for global exponential stability of the neural networks are established and an estimate of the exponential decay rate is also derived for each case.

AB - In this paper, the exponential stability of nonlinear discrete-time systems is studied. A novel notion of nonlinear spectral radius is defined. Under the assumption of Lipschitz continuity for the activation function, the developed approach is applied to stability analysis of discrete-time neural networks. A series of sufficient conditions for global exponential stability of the neural networks are established and an estimate of the exponential decay rate is also derived for each case.

UR - http://www.scopus.com/inward/record.url?scp=33745993334&partnerID=8YFLogxK

U2 - 10.1016/j.chaos.2005.09.075

DO - 10.1016/j.chaos.2005.09.075

M3 - Journal article

SN - 0960-0779

VL - 31

SP - 424

EP - 436

JO - Chaos, Solitons and Fractals

JF - Chaos, Solitons and Fractals

IS - 2

ER -

A new stability criterion for discrete-time neural networks: Nonlinear spectral radius

Abstract

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this