Adaptive error-constrained backpropagation algorithm

Sooyong Choi, Kyun Byoung Ko, Daesik Hong

Research output: Contribution to conferencePaper

Abstract

In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm are applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise valance. By means of extention and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm and its simplified algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.

Original languageEnglish
Pages103-112
Number of pages10
Publication statusPublished - 2001 Dec 1

Fingerprint

Backpropagation algorithms
Constrained optimization
Adaptive filters

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

@conference{8d87ae19df3d40b7ba53c9c2983ceee8,
title = "Adaptive error-constrained backpropagation algorithm",
abstract = "In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm are applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise valance. By means of extention and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm and its simplified algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.",
author = "Sooyong Choi and Ko, {Kyun Byoung} and Daesik Hong",
year = "2001",
month = "12",
day = "1",
language = "English",
pages = "103--112",

}

Adaptive error-constrained backpropagation algorithm. / Choi, Sooyong; Ko, Kyun Byoung; Hong, Daesik.

2001. 103-112.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Adaptive error-constrained backpropagation algorithm

AU - Choi, Sooyong

AU - Ko, Kyun Byoung

AU - Hong, Daesik

PY - 2001/12/1

Y1 - 2001/12/1

N2 - In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm are applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise valance. By means of extention and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm and its simplified algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.

AB - In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm are applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise valance. By means of extention and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm and its simplified algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0035783572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035783572&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0035783572

SP - 103

EP - 112

ER -