Global Exponential Stability of a Class of Neural Networks With Unbounded and Varying Delays

DOI

10.2991/iske.2007.231How to use a DOI?

Keywords

neural networks; globally exponential stability; vector Liapunov function; unbounded delays

Abstract

Based on the theory of topological degree and properties of M-matrix, by constructing proper vector Lyapunov functions, the existence and uniqueness of the equilibrium point and its global exponential stability are investigated for a class of neural networks with unbounded and varying delays. Without assuming the boundedness and differentiability of the activation functions, several new sufficient criterions for ascertaining the existence, uniqueness and global exponential stability of the equilibrium point of such neural networks are obtained. Since the criterion is independent of the delays and simplifies the calculation, it is easy to test the conditions of the criterion in practice. An example is given to demonstrate the feasibility of the criterion.

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Dianbo Ren
PY  - 2007/10
DA  - 2007/10
TI  - Global Exponential Stability of a Class of Neural Networks With Unbounded and Varying Delays
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1362
EP  - 1366
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.231
DO  - 10.2991/iske.2007.231
ID  - Ren2007/10
ER  -