Ensemble Separable Recurs ive Techniques for MLP Networks
Novel hybrid or separable recursive training strategies are proposed for the training of feedforward neural networks which include switching modules and ensemble between them. This new technique for updating weights combines nonlinear recursive training algorithms for the optimization of nonlinear w...
محفوظ في:
المؤلفون الرئيسيون: | , |
---|---|
التنسيق: | مقال |
منشور في: |
Australian National University
2010
|
الموضوعات: | |
الوصول للمادة أونلاين: | http://cs.anu.edu.au/ojs/index.php/ajiips http://eprints.utp.edu.my/3810/ |
الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
id |
my.utp.eprints.3810 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.38102014-04-01T06:06:58Z Ensemble Separable Recurs ive Techniques for MLP Networks Asirvadam , Vijanth Sagayan McLoone, Sean TK Electrical engineering. Electronics Nuclear engineering QA75 Electronic computers. Computer science Novel hybrid or separable recursive training strategies are proposed for the training of feedforward neural networks which include switching modules and ensemble between them. This new technique for updating weights combines nonlinear recursive training algorithms for the optimization of nonlinear weights with recursive least square (RLS) type algorithms for the training of linear weights in one integrated routine. The proposed new variant of hybrid weight update includes two form of switching mechanism based on the condition of input data to the system (correlated or random). The performance switching modules and dual ensembling approach on switching mechanism is illustrated by the simulation studies. Simulation results demonstrate the superiority of the new proposed hybrid variant training schemes compared to traditional recursive prediction schemes using various chaotic non-linear benchmark problems. Australian National University 2010 Article PeerReviewed http://cs.anu.edu.au/ojs/index.php/ajiips Asirvadam , Vijanth Sagayan and McLoone, Sean (2010) Ensemble Separable Recurs ive Techniques for MLP Networks. Australian Journal of Intelligent Information Processing Systems, 12 (4). pp. 7-12. ISSN 1321-2133 http://eprints.utp.edu.my/3810/ |
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 McLoone, Sean Ensemble Separable Recurs ive Techniques for MLP Networks |
description |
Novel hybrid or separable recursive training strategies are proposed for the training of feedforward neural networks which include switching modules and ensemble between them. This new technique for updating weights combines nonlinear recursive training algorithms for the optimization of nonlinear weights with recursive least square (RLS) type algorithms for the training of linear weights in one integrated routine. The proposed new variant of hybrid weight update includes two form of switching mechanism based on the condition of input data to the system (correlated or random). The performance switching modules and dual ensembling approach on switching mechanism is illustrated by the simulation studies. Simulation results demonstrate the superiority of the new proposed hybrid variant training schemes compared to traditional recursive prediction schemes using various chaotic non-linear benchmark problems. |
format |
Article |
author |
Asirvadam , Vijanth Sagayan McLoone, Sean |
author_facet |
Asirvadam , Vijanth Sagayan McLoone, Sean |
author_sort |
Asirvadam , Vijanth Sagayan |
title |
Ensemble Separable Recurs ive Techniques for MLP Networks |
title_short |
Ensemble Separable Recurs ive Techniques for MLP Networks |
title_full |
Ensemble Separable Recurs ive Techniques for MLP Networks |
title_fullStr |
Ensemble Separable Recurs ive Techniques for MLP Networks |
title_full_unstemmed |
Ensemble Separable Recurs ive Techniques for MLP Networks |
title_sort |
ensemble separable recurs ive techniques for mlp networks |
publisher |
Australian National University |
publishDate |
2010 |
url |
http://cs.anu.edu.au/ojs/index.php/ajiips http://eprints.utp.edu.my/3810/ |
_version_ |
1738655297140948992 |
score |
13.154905 |