Global robust exponential stability analysis for interval recurrent neural networks

Shengyuan Xu; James Lam; Daniel W.C. Ho; Yun Zou

doi:10.1016/j.physleta.2004.03.038

Author(s)

Shengyuan Xu
James Lam
Daniel W.C. Ho
Yun Zou

Related Research Unit(s)

Department of Mathematics

Detail(s)

Original language	English
Pages (from-to)	124-133
Journal / Publication	Physics Letters, Section A: General, Atomic and Solid State Physics
Volume	325
Issue number	2
Publication status	Published - 10 May 2004

Link(s)

DOI	DOI https://doi.org/10.1016/j.physleta.2004.03.038 Final Published version
	Check@CityULib
Link to Scopus	https://www.scopus.com/record/display.uri?eid=2-s2.0-1942443174&origin=recordpage
Permanent Link	https://scholars.cityu.edu.hk/en/publications/publication(a3c44b3b-68e3-448c-a956-bae7fe5f3719).html

Abstract

This Letter investigates the problem of robust global exponential stability analysis for interval recurrent neural networks (RNNs) via the linear matrix inequality (LMI) approach. The values of the time-invariant uncertain parameters are assumed to be bounded within given compact sets. An improved condition for the existence of a unique equilibrium point and its global exponential stability of RNNs with known parameters is proposed. Based on this, a sufficient condition for the global robust exponential stability for interval RNNs is obtained. Both of the conditions are expressed in terms of LMIs, which can be checked easily by various recently developed convex optimization algorithms. Examples are provided to demonstrate the reduced conservatism of the proposed exponential stability condition. © 2004 Elsevier B.V. All rights reserved.

Research Area(s)

Global exponential stability, Interval systems, Linear matrix inequality, Recurrent neural networks

Citation Format(s)

[ RIS ] [ BibTeX ]

Global robust exponential stability analysis for interval recurrent neural networks. / Xu, Shengyuan; Lam, James; Ho, Daniel W.C. et al.

In: Physics Letters, Section A: General, Atomic and Solid State Physics, Vol. 325, No. 2, 10.05.2004, p. 124-133.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review

Xu, S, Lam, J, Ho, DWC & Zou, Y 2004, 'Global robust exponential stability analysis for interval recurrent neural networks', Physics Letters, Section A: General, Atomic and Solid State Physics, vol. 325, no. 2, pp. 124-133. https://doi.org/10.1016/j.physleta.2004.03.038

Xu, S., Lam, J., Ho, D. W. C., & Zou, Y. (2004). Global robust exponential stability analysis for interval recurrent neural networks. Physics Letters, Section A: General, Atomic and Solid State Physics, 325(2), 124-133. https://doi.org/10.1016/j.physleta.2004.03.038

Xu S, Lam J, Ho DWC, Zou Y. Global robust exponential stability analysis for interval recurrent neural networks. Physics Letters, Section A: General, Atomic and Solid State Physics. 2004 May 10;325(2):124-133. doi: 10.1016/j.physleta.2004.03.038

Xu, Shengyuan ; Lam, James ; Ho, Daniel W.C. et al. / Global robust exponential stability analysis for interval recurrent neural networks. In: Physics Letters, Section A: General, Atomic and Solid State Physics. 2004 ; Vol. 325, No. 2. pp. 124-133.