Fast and efficient sequential learning algorithms using direct-link RBF networks
Novel fast and efficient sequential learning algorithms are proposed for direct-link radial basis function (DRBF) networks. The dynamic DRBF network is trained using the recently proposed decomposed/parallel recursive Levenberg Marquardt (PRLM) algorithm by neglecting the interneuron weight interact...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Book Section |
Published: |
IEEE Press
2003
|
Subjects: | |
Online Access: | http://isp.imm.dtu.dk/nnsp2003 http://eprints.utp.edu.my/3828/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.3828 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.38282011-01-04T00:42:19Z Fast and efficient sequential learning algorithms using direct-link RBF networks Asirvadam , Vijanth Sagayan McLoone, Sean Irwin, George TK Electrical engineering. Electronics Nuclear engineering Novel fast and efficient sequential learning algorithms are proposed for direct-link radial basis function (DRBF) networks. The dynamic DRBF network is trained using the recently proposed decomposed/parallel recursive Levenberg Marquardt (PRLM) algorithm by neglecting the interneuron weight interactions. The resulting sequential learning approach enables weights to be updated in an efficient parallel manner and facilitates a minimal update extension for real-time applications. Simulation results for two benchmark problems show the feasibility of the new training algorithms. IEEE Press Christophe , Molina Tülay , Adali Jan , Larsen Marc , Van Hulle 2003 Book Section PeerReviewed http://isp.imm.dtu.dk/nnsp2003 Asirvadam , Vijanth Sagayan and McLoone, Sean and Irwin, George (2003) Fast and efficient sequential learning algorithms using direct-link RBF networks. In: Neural Networks For Signal Processing XIII. NEURAL NETWORKS For SIGNAL PROCESSING (XIII). IEEE Press, Piscataway, New Jersey, pp. 209-218. ISBN 0-7803-8178-5 http://eprints.utp.edu.my/3828/ |
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 |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Asirvadam , Vijanth Sagayan McLoone, Sean Irwin, George Fast and efficient sequential learning algorithms using direct-link RBF networks |
description |
Novel fast and efficient sequential learning algorithms are proposed for direct-link radial basis function (DRBF) networks. The dynamic DRBF network is trained using the recently proposed decomposed/parallel recursive Levenberg Marquardt (PRLM) algorithm by neglecting the interneuron weight interactions. The resulting sequential learning approach enables weights to be updated in an efficient parallel manner and facilitates a minimal update extension for real-time applications. Simulation results for two benchmark problems show the feasibility of the new training algorithms. |
author2 |
Christophe , Molina |
author_facet |
Christophe , Molina Asirvadam , Vijanth Sagayan McLoone, Sean Irwin, George |
format |
Book Section |
author |
Asirvadam , Vijanth Sagayan McLoone, Sean Irwin, George |
author_sort |
Asirvadam , Vijanth Sagayan |
title |
Fast and efficient sequential learning algorithms using direct-link RBF networks |
title_short |
Fast and efficient sequential learning algorithms using direct-link RBF networks |
title_full |
Fast and efficient sequential learning algorithms using direct-link RBF networks |
title_fullStr |
Fast and efficient sequential learning algorithms using direct-link RBF networks |
title_full_unstemmed |
Fast and efficient sequential learning algorithms using direct-link RBF networks |
title_sort |
fast and efficient sequential learning algorithms using direct-link rbf networks |
publisher |
IEEE Press |
publishDate |
2003 |
url |
http://isp.imm.dtu.dk/nnsp2003 http://eprints.utp.edu.my/3828/ |
_version_ |
1738655299382804480 |
score |
13.19449 |