Abstract
A global stability analysis of a particular class of recurrent neural networks with time-varying delay is performed. Both Lipschitz continuous and monotone non-decreasing activation functions are considered. Globally asymptotically delay-dependent stability criteria are derived in the form of linear matrix inequalities through the use of Leibniz-Newton formula and relaxation matrices. Finally, two numerical examples are given to illustrate the effectiveness of the given criterion.
| Original language | English |
|---|---|
| Pages (from-to) | 736-742 |
| Number of pages | 7 |
| Journal | IET Control Theory and Applications |
| Volume | 2 |
| Issue number | 8 |
| DOIs | |
| Publication status | Published - 2008 Jul 24 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Human-Computer Interaction
- Computer Science Applications
- Control and Optimization
- Electrical and Electronic Engineering
Cite this
}
Delay-dependent stability analysis for recurrent neural networks with time-varying delay. / Lu, Chien-Yu; Su, T. J.; Huang, S. C.
In: IET Control Theory and Applications, Vol. 2, No. 8, 24.07.2008, p. 736-742.Research output: Contribution to journal › Article
TY - JOUR
T1 - Delay-dependent stability analysis for recurrent neural networks with time-varying delay
AU - Lu, Chien-Yu
AU - Su, T. J.
AU - Huang, S. C.
PY - 2008/7/24
Y1 - 2008/7/24
N2 - A global stability analysis of a particular class of recurrent neural networks with time-varying delay is performed. Both Lipschitz continuous and monotone non-decreasing activation functions are considered. Globally asymptotically delay-dependent stability criteria are derived in the form of linear matrix inequalities through the use of Leibniz-Newton formula and relaxation matrices. Finally, two numerical examples are given to illustrate the effectiveness of the given criterion.
AB - A global stability analysis of a particular class of recurrent neural networks with time-varying delay is performed. Both Lipschitz continuous and monotone non-decreasing activation functions are considered. Globally asymptotically delay-dependent stability criteria are derived in the form of linear matrix inequalities through the use of Leibniz-Newton formula and relaxation matrices. Finally, two numerical examples are given to illustrate the effectiveness of the given criterion.
UR - http://www.scopus.com/inward/record.url?scp=47549110558&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=47549110558&partnerID=8YFLogxK
U2 - 10.1049/iet-cta:20070313
DO - 10.1049/iet-cta:20070313
M3 - Article
AN - SCOPUS:47549110558
VL - 2
SP - 736
EP - 742
JO - IET Control Theory and Applications
JF - IET Control Theory and Applications
SN - 1751-8644
IS - 8
ER -