A fully adaptive normalized nonlinear gradient descent algorithm for nonlinear system identification

Author

Krcmar, Igor R. ; Mandic, Danilo P.

Author_Institution

Fac. of Electr. Eng., Banjaluka Univ., Bosnia-Herzegovina

Volume

6

fYear

2001

fDate

2001

Firstpage

3493

Abstract

A fully adaptive normalized nonlinear gradient descent (FANNGD) algorithm for neural adaptive filters employed for nonlinear system identification is proposed. This full adaptation is achieved using the instantaneous squared prediction error to adapt the free parameter of the NNGD algorithm. The convergence analysis of the proposed algorithm is undertaken using the contractivity property of the nonlinear activation function of a neuron. Simulation results show that a fully adaptive NNGD algorithm outperforms the standard NNGD algorithm for nonlinear system identification

Keywords

adaptive filters; adaptive signal processing; convergence of numerical methods; filtering theory; gradient methods; identification; neural nets; nonlinear filters; FANNGD algorithm; adaptive algorithm; contractivity property; convergence analysis; gradient descent algorithm; instantaneous squared prediction error; neural adaptive filters; nonlinear activation function; nonlinear system identification; normalized nonlinear algorithm; Adaptive filters; Algorithm design and analysis; Convergence; Cost function; Education; Information systems; Neurons; Nonlinear equations; Nonlinear systems; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on

Conference_Location

Salt Lake City, UT

ISSN

1520-6149

Print_ISBN

0-7803-7041-4

Type

conf

DOI

10.1109/ICASSP.2001.940594

Filename

940594