A new stability condition of neural networks with time-varying delay

Yun Chen; Wei Xing Zheng

doi:10.1109/WCICA.2012.6357894

A new stability condition of neural networks with time-varying delay

Yun Chen
, Wei Xing Zheng

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

Abstract

This paper discusses stability of neural networks (NNs) with time-varying delay. Delay-fractioning Lyapunov- Krasovskii functional (LKF) method and convex analysis are applied to establish a new stability condition. Two possible cases for the delay are taken into account when the delay interval is equivalently divided into two subintervals. The maximal allowable delay that ensures global asymptotical stability of the neural network under consideration can be computed by solving a set of linear matrix inequalities (LMIs). The advantage of the method is illustrated by numerical examples.

Original language	English
Title of host publication	Proceedings of the 10th World Congress on Intelligent Control and Automation, July 6-8, 2012, Beijing, China
Publisher	IEEE
Pages	336-340
Number of pages	5
ISBN (Print)	9781467313988
DOIs	https://doi.org/10.1109/WCICA.2012.6357894
Publication status	Published - 2012
Event	World Congress on Intelligent Control and Automation - Duration: 6 Jul 2012 → …

Conference

Conference	World Congress on Intelligent Control and Automation
Period	6/07/12 → …

Keywords

delay
neural networks (computer science)
stability
time-varying systems

Access to Document

10.1109/WCICA.2012.6357894

Cite this

@inproceedings{650b84cd1ea1446f9e6e5d6477d1db9c,

title = "A new stability condition of neural networks with time-varying delay",

abstract = "This paper discusses stability of neural networks (NNs) with time-varying delay. Delay-fractioning Lyapunov- Krasovskii functional (LKF) method and convex analysis are applied to establish a new stability condition. Two possible cases for the delay are taken into account when the delay interval is equivalently divided into two subintervals. The maximal allowable delay that ensures global asymptotical stability of the neural network under consideration can be computed by solving a set of linear matrix inequalities (LMIs). The advantage of the method is illustrated by numerical examples.",

keywords = "delay, neural networks (computer science), stability, time-varying systems",

author = "Yun Chen and Zheng, \{Wei Xing\}",

year = "2012",

doi = "10.1109/WCICA.2012.6357894",

language = "English",

isbn = "9781467313988",

pages = "336--340",

booktitle = "Proceedings of the 10th World Congress on Intelligent Control and Automation, July 6-8, 2012, Beijing, China",

publisher = "IEEE",

note = "World Congress on Intelligent Control and Automation ; Conference date: 06-07-2012",

}

TY - GEN

T1 - A new stability condition of neural networks with time-varying delay

AU - Chen, Yun

AU - Zheng, Wei Xing

PY - 2012

Y1 - 2012

N2 - This paper discusses stability of neural networks (NNs) with time-varying delay. Delay-fractioning Lyapunov- Krasovskii functional (LKF) method and convex analysis are applied to establish a new stability condition. Two possible cases for the delay are taken into account when the delay interval is equivalently divided into two subintervals. The maximal allowable delay that ensures global asymptotical stability of the neural network under consideration can be computed by solving a set of linear matrix inequalities (LMIs). The advantage of the method is illustrated by numerical examples.

AB - This paper discusses stability of neural networks (NNs) with time-varying delay. Delay-fractioning Lyapunov- Krasovskii functional (LKF) method and convex analysis are applied to establish a new stability condition. Two possible cases for the delay are taken into account when the delay interval is equivalently divided into two subintervals. The maximal allowable delay that ensures global asymptotical stability of the neural network under consideration can be computed by solving a set of linear matrix inequalities (LMIs). The advantage of the method is illustrated by numerical examples.

KW - delay

KW - neural networks (computer science)

KW - stability

KW - time-varying systems

UR - http://handle.uws.edu.au:8081/1959.7/524061

UR - http://2012.wcica.info/

U2 - 10.1109/WCICA.2012.6357894

DO - 10.1109/WCICA.2012.6357894

M3 - Conference Paper

SN - 9781467313988

SP - 336

EP - 340

BT - Proceedings of the 10th World Congress on Intelligent Control and Automation, July 6-8, 2012, Beijing, China

PB - IEEE

T2 - World Congress on Intelligent Control and Automation

Y2 - 6 July 2012

ER -

A new stability condition of neural networks with time-varying delay

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this