A semi-free weighting matrices approach for neutral-type delayed neural networks

Authors:
Huanhuan Mai;Xiaofeng Liao;Chuandong Li
Affiliations:
Department of Computer Science and Engineering, Chongqing University, Chongqing, 400030, PR China;Department of Computer Science and Engineering, Chongqing University, Chongqing, 400030, PR China;Department of Computer Science and Engineering, Chongqing University, Chongqing, 400030, PR China
Venue:
Journal of Computational and Applied Mathematics
Year:
2009

Citing 8
Cited 4

A new delay-dependent criterion for neural systems with multiple delays

Journal of Computational and Applied Mathematics
Stability of Time-Delay Systems

Stability of Time-Delay Systems
Brief paper: Delay-dependent robust stabilization for uncertain neutral systems with distributed delays

Automatica (Journal of IFAC)
Small-signal stability criterion for electrical networks containing lossless transmission lines

IBM Journal of Research and Development
Delay-dependent exponential stability for a class of neural networks with time delays

Journal of Computational and Applied Mathematics
Novel delay-dependent exponential stability analysis for a class of delayed neural networks

ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I
Time-delay neural networks for estimating lip movements from speech analysis: a useful tool in audio-video synchronization

IEEE Transactions on Circuits and Systems for Video Technology
A delayed neural network for solving linear projection equations and its analysis

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	7.29

Visualization

Abstract

In this paper, a new approach is proposed for stability issues of neutral-type neural networks (DNNs) with constant delay. First, the semi-free weighting matrices are proposed and used instead of the known free weighting matrices to express the relationship between the terms in the Leibniz-Newton formula to simplify the system synthesis and to obtain less computation demand. Second, global exponential stability conditions which are less conservative and restrictive than the known results are derived. At the same time, based on the above approach, fewer variable matrices are introduced in the construction of the Lyapunov functional and augmented Lyapunov functional. Two examples are given to show their effectiveness and advantages over others.