Letters: Less conservative delay-dependent stability criteria for neural networks with time-varying delays

Authors:
Hanyong Shao
Affiliations:
School of Electrical and Information Automation, Qufu Normal University, Rizhao, Shandong 276826, China
Venue:
Neurocomputing
Year:
2010

Citing 4
Cited 1

Backpropagation in perceptrons with feedback

Neural Computers
A comparative study of two modeling approaches in neural networks

Neural Networks
Improved delay-dependent exponential stability criteria for discrete-time recurrent neural networks with time-varying delays

Neurocomputing
Neural network for quadratic optimization with bound constraints

IEEE Transactions on Neural Networks

New criteria for exponential stability of delayed recurrent neural networks

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper is concerned with the stability for static neural networks with time-varying delays. With an appropriate Lyapunov functional formulated, a new technique is proposed to up bound the derivative of the Lyapunov functional. A delay-dependent stability criterion is obtained by proving the bound negative definite with convex combination methods. The delay-dependent stability criterion is simpler and less conservative than some existing ones. Both delay-independent and delay-dependent criteria are obtained, which can be checked easily using the recently developed algorithms. Examples are provided to illustrate the effectiveness and the reduced conservatism of the proposed results.