Cover Image

Separable Recursive Training Algorithms with Switching Module

A novel hybrid or separable recursive training strategies are de rived for the training of feedforward neural networks which incoporates a switching module. This new technique for updating weights combines non linear recursive training algorithms for the optimization of nonlinear weights with recurs...

Full description

Saved in:
Bibliographic Details
Main Author: Asirvadam , Vijanth Sagayan
Other Authors: Leung , Chi-Sing
Format: Book Section
Published: Springer 2009
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
QA75 Electronic computers. Computer science
Online Access:http://www.springerlink.com/content/41g22372271138w5/
http://eprints.utp.edu.my/3814/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.3814
record_format eprints
spelling my.utp.eprints.38142011-01-04T00:39:26Z Separable Recursive Training Algorithms with Switching Module Asirvadam , Vijanth Sagayan TK Electrical engineering. Electronics Nuclear engineering QA75 Electronic computers. Computer science A novel hybrid or separable recursive training strategies are de rived for the training of feedforward neural networks which incoporates a switching module. This new technique for updating weights combines non linear recursive training algorithms for the optimization of nonlinear weights with recursive least square type algorithms for the training of linear weights in one integrated routine. The proposed new variant of hybrid weight update includes switching mechanism based on the condition of input data to the system (correlated or noncorrelated). Simulation results demonstrate the im provement of the new proposed switching mode training scheme. Springer Leung , Chi-Sing Minho, Lee Chan, H-Chan 2009 Book Section PeerReviewed http://www.springerlink.com/content/41g22372271138w5/ Asirvadam , Vijanth Sagayan (2009) Separable Recursive Training Algorithms with Switching Module. In: Lecture Notes in Computer Science. Springer. ISBN 364210682X http://eprints.utp.edu.my/3814/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
topic TK Electrical engineering. Electronics Nuclear engineering
QA75 Electronic computers. Computer science
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
QA75 Electronic computers. Computer science
Asirvadam , Vijanth Sagayan
Separable Recursive Training Algorithms with Switching Module
description A novel hybrid or separable recursive training strategies are de rived for the training of feedforward neural networks which incoporates a switching module. This new technique for updating weights combines non linear recursive training algorithms for the optimization of nonlinear weights with recursive least square type algorithms for the training of linear weights in one integrated routine. The proposed new variant of hybrid weight update includes switching mechanism based on the condition of input data to the system (correlated or noncorrelated). Simulation results demonstrate the im provement of the new proposed switching mode training scheme.
author2 Leung , Chi-Sing
author_facet Leung , Chi-Sing
Asirvadam , Vijanth Sagayan
format Book Section
author Asirvadam , Vijanth Sagayan
author_sort Asirvadam , Vijanth Sagayan
title Separable Recursive Training Algorithms with Switching Module
title_short Separable Recursive Training Algorithms with Switching Module
title_full Separable Recursive Training Algorithms with Switching Module
title_fullStr Separable Recursive Training Algorithms with Switching Module
title_full_unstemmed Separable Recursive Training Algorithms with Switching Module
title_sort separable recursive training algorithms with switching module
publisher Springer
publishDate 2009
url http://www.springerlink.com/content/41g22372271138w5/
http://eprints.utp.edu.my/3814/
_version_ 1738655297728151552
score 13.160551

Similar Items