A Recurrent Neural Network for Solving a Class of General Variational Inequalities

Author

Hu, Xiaolin ; Wang, Jun

Author_Institution

Dept. of Autom. & Comput.-Aided Eng., Chinese Univ. of Hong Kong

Volume

37

Issue

3

fYear

2007

fDate

6/1/2007 12:00:00 AM

Firstpage

528

Lastpage

539

Abstract

This paper presents a recurrent neural-network model for solving a special class of general variational inequalities (GVIs), which includes classical VIs as special cases. It is proved that the proposed neural network (NN) for solving this class of GVIs can be globally convergent, globally asymptotically stable, and globally exponentially stable under different conditions. The proposed NN can be viewed as a modified version of the general projection NN existing in the literature. Several numerical examples are provided to demonstrate the effectiveness and performance of the proposed NN

Keywords

mathematics computing; recurrent neural nets; variational techniques; asymptotic stability; general variational inequalities; recurrent neural network; Asymptotic stability; Control systems; Convergence; Equations; Iterative methods; Matrices; Neural networks; Pattern recognition; Quadratic programming; Recurrent neural networks; General projection neural network (GPNN); general variational inequalities (GVIs); global asymptotic stability; global exponential stability; recurrent neural network; Algorithms; Computer Simulation; Decision Support Techniques; Feedback; Mathematical Computing; Models, Theoretical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/TSMCB.2006.886166

Filename

4200801