Nonlinear FIR adaptive filters with a gradient adaptive amplitude in the nonlinearity

A nonlinear gradient descent (NGD) learning algorithm with an adaptive amplitude of the nonlinearity is derived for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perceptron). This is based on the adaptive amplitude backpropagation (AABP) algorithm for large-scale n...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2002-08, Vol.9 (8), p.253-255
Main Authors: Hanna, A.I., Mandic, D.P.
Format: Article
Language:English
Subjects:
Adaptive algorithms
Adaptive filters
Algorithms
Amplitudes
Backpropagation algorithms
Biomedical signal processing
Constraint optimization
Descent
Filtering algorithms
Finite impulse response filter
Impulse response
Large-scale systems
Neural networks
Nonlinearity
Signal processing
Signal processing algorithms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A nonlinear gradient descent (NGD) learning algorithm with an adaptive amplitude of the nonlinearity is derived for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perceptron). This is based on the adaptive amplitude backpropagation (AABP) algorithm for large-scale neural networks. The amplitude of the nonlinear activation function is made gradient adaptive to give the adaptive amplitude nonlinear gradient descent (AANGD) algorithm, making the AANGD suitable for processing nonlinear and nonstationary input signals with a large dynamical range. Experimental results show the AANGD algorithm outperforming the standard NGD algorithm on both colored and nonlinear input with large dynamics. Despite its simplicity, the considered algorithm proves suitable for adaptive filtering of nonlinear and nonstationary signals.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2002.803001