Globally asymptotic stability of a class of neutral-type neural networks with delays

Chao Jung Cheng; Teh-Lu Liao; Jun Juh Yan; Chi-Chuan Hwang

doi:10.1109/TSMCB.2006.874677

Globally asymptotic stability of a class of neutral-type neural networks with delays

Chao Jung Cheng, Teh-Lu Liao, Jun Juh Yan, Chi-Chuan Hwang

Department of Engineering Science

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

71 Citations (Scopus)

Abstract

Several stability conditions for a class of systems with retarded-type delays are presented in the literature. However, no results have yet been presented for neural networks with neutral-type delays. Accordingly, this correspondence investigates the globally asymptotic stability of a class of neutral-type neural networks with delays. This class of systems includes Hopfield neural networks, cellular neural networks, and Cohen-Grossberg neural networks. Based on the Lyapunov stability method, two delay-independent sufficient stability conditions are derived. These stability conditions are easily checked and can be derived from the connection matrix and the network parameters without the requirement for any assumptions regarding the symmetry of the interconnections. Two illustrative examples are presented to demonstrate the validity of the proposed stability criteria.

Original language	English
Pages (from-to)	1191-1195
Number of pages	5
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	36
Issue number	5
DOIs	https://doi.org/10.1109/TSMCB.2006.874677
Publication status	Published - 2006 Oct 1

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Artificial Intelligence
Human-Computer Interaction

Access to Document

10.1109/TSMCB.2006.874677

Fingerprint Dive into the research topics of 'Globally asymptotic stability of a class of neutral-type neural networks with delays'. Together they form a unique fingerprint.

Cite this

@article{fd06aafd4c1e43c797d374e048424e42,

title = "Globally asymptotic stability of a class of neutral-type neural networks with delays",

abstract = "Several stability conditions for a class of systems with retarded-type delays are presented in the literature. However, no results have yet been presented for neural networks with neutral-type delays. Accordingly, this correspondence investigates the globally asymptotic stability of a class of neutral-type neural networks with delays. This class of systems includes Hopfield neural networks, cellular neural networks, and Cohen-Grossberg neural networks. Based on the Lyapunov stability method, two delay-independent sufficient stability conditions are derived. These stability conditions are easily checked and can be derived from the connection matrix and the network parameters without the requirement for any assumptions regarding the symmetry of the interconnections. Two illustrative examples are presented to demonstrate the validity of the proposed stability criteria.",

author = "Cheng, {Chao Jung} and Teh-Lu Liao and Yan, {Jun Juh} and Chi-Chuan Hwang",

year = "2006",

month = oct,

day = "1",

doi = "10.1109/TSMCB.2006.874677",

language = "English",

volume = "36",

pages = "1191--1195",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - Globally asymptotic stability of a class of neutral-type neural networks with delays

AU - Cheng, Chao Jung

AU - Liao, Teh-Lu

AU - Yan, Jun Juh

AU - Hwang, Chi-Chuan

PY - 2006/10/1

Y1 - 2006/10/1

N2 - Several stability conditions for a class of systems with retarded-type delays are presented in the literature. However, no results have yet been presented for neural networks with neutral-type delays. Accordingly, this correspondence investigates the globally asymptotic stability of a class of neutral-type neural networks with delays. This class of systems includes Hopfield neural networks, cellular neural networks, and Cohen-Grossberg neural networks. Based on the Lyapunov stability method, two delay-independent sufficient stability conditions are derived. These stability conditions are easily checked and can be derived from the connection matrix and the network parameters without the requirement for any assumptions regarding the symmetry of the interconnections. Two illustrative examples are presented to demonstrate the validity of the proposed stability criteria.

AB - Several stability conditions for a class of systems with retarded-type delays are presented in the literature. However, no results have yet been presented for neural networks with neutral-type delays. Accordingly, this correspondence investigates the globally asymptotic stability of a class of neutral-type neural networks with delays. This class of systems includes Hopfield neural networks, cellular neural networks, and Cohen-Grossberg neural networks. Based on the Lyapunov stability method, two delay-independent sufficient stability conditions are derived. These stability conditions are easily checked and can be derived from the connection matrix and the network parameters without the requirement for any assumptions regarding the symmetry of the interconnections. Two illustrative examples are presented to demonstrate the validity of the proposed stability criteria.

UR - http://www.scopus.com/inward/record.url?scp=33749386815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749386815&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2006.874677

DO - 10.1109/TSMCB.2006.874677

M3 - Article

C2 - 17036823

AN - SCOPUS:33749386815

VL - 36

SP - 1191

EP - 1195

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 5

ER -