Abstract
The current paper performs a global robust stability analysis for a class of discrete-time recurrent neural networks (DRNNs) with norm-bounded time-varying parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. An appropriate type of Lyapunov functional is proposed to establish the sufficient conditions for the DRNNs. The criteria are formulated by means of the feasibility of linear matrix inequalities (LMIs), which can be easily checked in practice. Two numerical examples are given to illustrate the effectiveness and applicability.
| Original language | English |
|---|---|
| Pages (from-to) | 1123-1132 |
| Number of pages | 10 |
| Journal | Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering |
| Volume | 221 |
| Issue number | 8 |
| DOIs | |
| Publication status | Published - 2007 Dec 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
Cite this
}
A delay-range-dependent approach to global robust stability for discrete-time uncertain recurrent neural networks with interval time-varying delay. / Lu, Chien-Yu.
In: Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering, Vol. 221, No. 8, 01.12.2007, p. 1123-1132.Research output: Contribution to journal › Article
TY - JOUR
T1 - A delay-range-dependent approach to global robust stability for discrete-time uncertain recurrent neural networks with interval time-varying delay
AU - Lu, Chien-Yu
PY - 2007/12/1
Y1 - 2007/12/1
N2 - The current paper performs a global robust stability analysis for a class of discrete-time recurrent neural networks (DRNNs) with norm-bounded time-varying parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. An appropriate type of Lyapunov functional is proposed to establish the sufficient conditions for the DRNNs. The criteria are formulated by means of the feasibility of linear matrix inequalities (LMIs), which can be easily checked in practice. Two numerical examples are given to illustrate the effectiveness and applicability.
AB - The current paper performs a global robust stability analysis for a class of discrete-time recurrent neural networks (DRNNs) with norm-bounded time-varying parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. An appropriate type of Lyapunov functional is proposed to establish the sufficient conditions for the DRNNs. The criteria are formulated by means of the feasibility of linear matrix inequalities (LMIs), which can be easily checked in practice. Two numerical examples are given to illustrate the effectiveness and applicability.
UR - http://www.scopus.com/inward/record.url?scp=37549045167&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=37549045167&partnerID=8YFLogxK
U2 - 10.1243/09596518JSCE451
DO - 10.1243/09596518JSCE451
M3 - Article
AN - SCOPUS:37549045167
VL - 221
SP - 1123
EP - 1132
JO - Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering
JF - Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering
SN - 0959-6518
IS - 8
ER -