A general recurrent neural network model for time-varying matrix inversion

Author

Zhang, Yunong ; Ge, Shuzhi Sam

Author_Institution

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

Volume

6

fYear

2003

fDate

9-12 Dec. 2003

Firstpage

6169

Abstract

This paper presents a general recurrent neural network model for online inversion of time-varying matrices. Utilizing the first-order time-derivative, the neural model guarantees its state trajectory globally converge to the exact inverse of a given time-varying matrix. In addition, exponential convergence can be achieved if linear or sigmoid activation function is used. Network sensitivity is also studied to show the desirable robustness property of this neural approach. Simulation results, including the application to kinematic control of redundant manipulators, are used to demonstrate the effectiveness and performance of the proposed neural model.

Keywords

convergence; matrix inversion; neurocontrollers; recurrent neural nets; redundant manipulators; time-varying systems; exponential convergence; manipulators; network sensitivity; online matrix inversion; recurrent neural network; sigmoid activation function; time-varying matrix; Application software; Concurrent computing; Convergence; Cost function; Digital arithmetic; Large-scale systems; Neural networks; Recurrent neural networks; Robot kinematics; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 2003. Proceedings. 42nd IEEE Conference on

ISSN

0191-2216

Print_ISBN

0-7803-7924-1

Type

conf

DOI

10.1109/CDC.2003.1272262

Filename

1272262