Conjugate gradient algorithm for series cascade nonlinear adaptive filters

C. Radhakrishnan, W. K. Jenkins, A. K. Garga

Research output: Contribution to journalArticle

Abstract

This paper considers series-cascade nonlinear filter architectures consisting of a linear FIR input filter, a memoryless polynomial nonlinearity, and a linear FIR/IIR output filter (LNL). Earlier publications reported on the development of the LMS and RLS backpropagation algorithms for training this same adaptive filter structure. In this paper the Conjugate Gradient backpropagation algorithm is derived for the joint adaptation of the LNL structure. An echo cancellation example is considered to study the algorithm in terms of its learning characteristics and computational complexity.

Original languageEnglish (US)
JournalMidwest Symposium on Circuits and Systems
Volume2
StatePublished - 2004

Fingerprint

Backpropagation algorithms
Adaptive filters
Echo suppression
Computational complexity
Polynomials

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

@article{992349b25dd7413097cda80cbd87e566,
title = "Conjugate gradient algorithm for series cascade nonlinear adaptive filters",
abstract = "This paper considers series-cascade nonlinear filter architectures consisting of a linear FIR input filter, a memoryless polynomial nonlinearity, and a linear FIR/IIR output filter (LNL). Earlier publications reported on the development of the LMS and RLS backpropagation algorithms for training this same adaptive filter structure. In this paper the Conjugate Gradient backpropagation algorithm is derived for the joint adaptation of the LNL structure. An echo cancellation example is considered to study the algorithm in terms of its learning characteristics and computational complexity.",
author = "C. Radhakrishnan and Jenkins, {W. K.} and Garga, {A. K.}",
year = "2004",
language = "English (US)",
volume = "2",
journal = "Midwest Symposium on Circuits and Systems",
issn = "1548-3746",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Conjugate gradient algorithm for series cascade nonlinear adaptive filters. / Radhakrishnan, C.; Jenkins, W. K.; Garga, A. K.

In: Midwest Symposium on Circuits and Systems, Vol. 2, 2004.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Conjugate gradient algorithm for series cascade nonlinear adaptive filters

AU - Radhakrishnan, C.

AU - Jenkins, W. K.

AU - Garga, A. K.

PY - 2004

Y1 - 2004

N2 - This paper considers series-cascade nonlinear filter architectures consisting of a linear FIR input filter, a memoryless polynomial nonlinearity, and a linear FIR/IIR output filter (LNL). Earlier publications reported on the development of the LMS and RLS backpropagation algorithms for training this same adaptive filter structure. In this paper the Conjugate Gradient backpropagation algorithm is derived for the joint adaptation of the LNL structure. An echo cancellation example is considered to study the algorithm in terms of its learning characteristics and computational complexity.

AB - This paper considers series-cascade nonlinear filter architectures consisting of a linear FIR input filter, a memoryless polynomial nonlinearity, and a linear FIR/IIR output filter (LNL). Earlier publications reported on the development of the LMS and RLS backpropagation algorithms for training this same adaptive filter structure. In this paper the Conjugate Gradient backpropagation algorithm is derived for the joint adaptation of the LNL structure. An echo cancellation example is considered to study the algorithm in terms of its learning characteristics and computational complexity.

UR - http://www.scopus.com/inward/record.url?scp=11144292805&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144292805&partnerID=8YFLogxK

M3 - Article

VL - 2

JO - Midwest Symposium on Circuits and Systems

JF - Midwest Symposium on Circuits and Systems

SN - 1548-3746

ER -