Stability analysis of high-order Hopfield type neural networks with uncertainty

Authors:
Bingji Xu;Qun Wang;Xiaoxin Liao
Affiliations:
School of Information Engineering, China University of Geosciences, Beijing 100083, China;School of Information Engineering, China University of Geosciences, Beijing 100083, China;Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
Venue:
Neurocomputing
Year:
2008

Citing 6
Cited 3

A stabilization algorithm for a class of uncertain linear systems

Systems & Control Letters
Parametric quadratic stabilizability of uncertain nonlinear systems

Systems & Control Letters
Global exponential stability of recurrent neural networks with time-varying delay

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Adaptive feedback linearization control of chaotic systems via recurrent high-order neural networks

Information Sciences: an International Journal
Stability analysis of Hopfield neural networks with uncertainty

Mathematical and Computer Modelling: An International Journal
Multiperiodicity of Discrete-Time Delayed Neural Networks Evoked by Periodic External Inputs

IEEE Transactions on Neural Networks

A Master-Slave Neural Network for precise recognition of the complicated hand operations based on EEG

International Journal of Advanced Media and Communication
Existence and global attractivity of almost periodic solutions for delayed high-ordered neural networks

Neurocomputing
Global Robust Exponential Stability of Uncertain Neutral High-Order Stochastic Hopfield Neural Networks with Time-Varying Delays

Neural Processing Letters

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, the stability of high-order Hopfield type neural networks with uncertainty is analyzed, the parametric uncertainty is assumed to be bounded. The equilibrium point position may exist for any particular unknown parameter vector in the parameter space, every time one or more of the uncertainty parameters is changed, the equilibrium may shift to a new position or altogether disappear. In the framework of parametric stability, some sufficient conditions are established to guarantee the existence of a globally asymptotically stable equilibrium point for all admissible parametric uncertainties, and the region about the equilibrium point of the nominal part of the neural network that contains the equilibria for each parameter vector in the given subset of the parameter space be estimated.