Multilayer neural network structure as Volterra filter

Author

Osowski, Stanislaw ; Quang, Thanh Vu

Author_Institution

Inst. of Theory of Electr. Eng. & Elec. Meas., Tech. Univ. Warsaw, Poland

Volume

6

fYear

1994

fDate

30 May-2 Jun 1994

Firstpage

253

Abstract

The paper presents the application of the successive linearization to the neural network implementation of the Volterra filter. Applying the signal flow graph approach the new learning rules for adaptation of weights of the obtained multilayer network structure are given. The presented multilayer structure is applied to signal processing including the identification of the parameters of the plant, noise canceling and signal prediction

Keywords

Volterra series; feedforward neural nets; filtering theory; interference (signal); learning (artificial intelligence); multilayer perceptrons; prediction theory; signal flow graphs; Volterra filter; learning rules; multilayer neural network structure; neural network implementation; noise canceling; signal flow graph approach; signal prediction; signal processing; successive linearization; weight adaptation; Equations; Finite impulse response filter; Flow graphs; Kernel; Multi-layer neural network; Neural networks; Nonhomogeneous media; Nonlinear filters; Signal processing; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on

Conference_Location

London

Print_ISBN

0-7803-1915-X

Type

conf

DOI

10.1109/ISCAS.1994.409564

Filename

409564