Global exponential estimates of stochastic interval neural networks with discrete and distributed delays
Global exponential estimates of stochastic interval neural networks with discrete and distributed delays
This paper is concerned with the robust exponential estimating problem for a class of neural networks with discrete and distributed delays. The considered neural networks are disturbed by Wiener processes, and possess interval uncertainties in the system parameters. A sufficient condition, which does not only guarantee the global exponential stability but also provides more exact characterizations on the decay rate and the coefficient, is established in terms of a novel Lyapunov–Krasovskii functional equipped with appropriately constructed exponential terms and the linear matrix inequality (LMI) technique. The estimates of the decay rate and the coefficient are obtained by solving a set of LMIs, which can be implemented easily by effective algorithms. In addition, slack matrices are introduced to reduce the conservatism of the condition. A numerical example is provided to illustrate the effectiveness of the theoretical results
discrete delay, distributed delay, exponential estimates, interval systems, linear matrix inequalities (lmis), stochastic neural networks
2950-2963
Shu, Zhan
ea5dc18c-d375-4db0-bbcc-dd0229f3a1cb
Lam, James
3eea3836-efda-430c-9ad4-ae4f3d4b8c4a
August 2008
Shu, Zhan
ea5dc18c-d375-4db0-bbcc-dd0229f3a1cb
Lam, James
3eea3836-efda-430c-9ad4-ae4f3d4b8c4a
Shu, Zhan and Lam, James
(2008)
Global exponential estimates of stochastic interval neural networks with discrete and distributed delays.
[in special issue: Artificial Neural Networks (ICANN 2006) / Engineering of Intelligent Systems (ICEIS 2006)]
Neurocomputing, 71 (13-15), .
(doi:10.1016/j.neucom.2007.07.003).
Abstract
This paper is concerned with the robust exponential estimating problem for a class of neural networks with discrete and distributed delays. The considered neural networks are disturbed by Wiener processes, and possess interval uncertainties in the system parameters. A sufficient condition, which does not only guarantee the global exponential stability but also provides more exact characterizations on the decay rate and the coefficient, is established in terms of a novel Lyapunov–Krasovskii functional equipped with appropriately constructed exponential terms and the linear matrix inequality (LMI) technique. The estimates of the decay rate and the coefficient are obtained by solving a set of LMIs, which can be implemented easily by effective algorithms. In addition, slack matrices are introduced to reduce the conservatism of the condition. A numerical example is provided to illustrate the effectiveness of the theoretical results
Text
SL08_NC.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
More information
e-pub ahead of print date: 24 July 2007
Published date: August 2008
Keywords:
discrete delay, distributed delay, exponential estimates, interval systems, linear matrix inequalities (lmis), stochastic neural networks
Organisations:
Mechatronics
Identifiers
Local EPrints ID: 199809
URI: http://eprints.soton.ac.uk/id/eprint/199809
ISSN: 0925-2312
PURE UUID: 23090892-d334-4e6f-8e3d-7c8cdb87612e
Catalogue record
Date deposited: 26 Oct 2011 08:37
Last modified: 14 Mar 2024 04:17
Export record
Altmetrics
Contributors
Author:
Zhan Shu
Author:
James Lam
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics