Convergence analysis of discrete time recurrent neural networks for linear variational inequality problem

Author

Tang, H.J. ; Tan, K.C. ; Zhang, Y.

Author_Institution

Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore

Volume

3

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

2470

Lastpage

2475

Abstract

We study the convergence of a class of discrete recurrent neural networks to solve linear variational inequality problem (LVIP). LVIP has important applications in engineering and economics. Not only the network´s exponential convergence for the case of positive definite matrix is proved, but its global convergence for positive semidefinite matrix is also proved. Conditions are derived to guarantee the convergences of the network. Comprehensive examples are discussed and simulated to illustrate the results

Keywords

convergence of numerical methods; eigenvalues and eigenfunctions; matrix algebra; optimisation; recurrent neural nets; convergence; discrete time neural networks; eigenvalues; linear variational inequality; optimization; positive definite matrix; positive semidefinite matrix; recurrent neural networks; Application software; Computer simulation; Continuous time systems; Convergence; Equations; Linear matrix inequalities; Neural networks; Recurrent neural networks; Symmetric matrices; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007530

Filename

1007530