A global-local artificial neural network with application to wave overtopping prediction

2.50
Hdl Handle:
http://hdl.handle.net/2173/31954
Title:
A global-local artificial neural network with application to wave overtopping prediction
Authors:
Wedge, David C.; Ingram, David M.; McLean, David A.; Mingham, Clive G.; Bandar, Zuhair A.
Citation:
Wedge, D.C. et al. A global-local artificial neural network with application to wave overtopping prediction. In Artificial Neural Networks: Formal Models and Their Applications - ICANN 2005, Springer, 2005, pp. 109-114
Publisher:
Springer
Issue Date:
2005
URI:
http://hdl.handle.net/2173/31954
DOI:
10.1007/11550907
Additional Links:
http://www.springerlink.com/content/105633/
Abstract:
We present a hybrid Radial Basis Function (RBF) - sigmoid neural network with a three-step training algorithm that utilises both global search and gradient descent training. We test the effectiveness of our method using four synthetic datasets and demonstrate its use in wave overtopping prediction. It is shown that the hybrid architecture is often superior to architectures containing neurons of a single type in several ways: lower errors are often achievable using fewer hidden neurons and with less need for regularisation. Our Global-Local Artificial Neural Network (GL-ANN) is also seen to compare favourably with both Perceptron Radial Basis Net (PRBFN) and Regression Tree RBFs
Type:
Book chapter
Language:
en
Description:
The original publication is available at http://www.springer.com/
ISSN:
0302-9743
EISSN:
1611-3349

Full metadata record

DC FieldValue Language
dc.contributor.authorWedge, David C.-
dc.contributor.authorIngram, David M.-
dc.contributor.authorMcLean, David A.-
dc.contributor.authorMingham, Clive G.-
dc.contributor.authorBandar, Zuhair A.-
dc.date.accessioned2008-07-14T15:11:41Z-
dc.date.available2008-07-14T15:11:41Z-
dc.date.issued2005-
dc.identifier.citationWedge, D.C. et al. A global-local artificial neural network with application to wave overtopping prediction. In Artificial Neural Networks: Formal Models and Their Applications - ICANN 2005, Springer, 2005, pp. 109-114en
dc.identifier.issn0302-9743-
dc.identifier.doi10.1007/11550907-
dc.identifier.urihttp://hdl.handle.net/2173/31954-
dc.descriptionThe original publication is available at http://www.springer.com/en
dc.description.abstractWe present a hybrid Radial Basis Function (RBF) - sigmoid neural network with a three-step training algorithm that utilises both global search and gradient descent training. We test the effectiveness of our method using four synthetic datasets and demonstrate its use in wave overtopping prediction. It is shown that the hybrid architecture is often superior to architectures containing neurons of a single type in several ways: lower errors are often achievable using fewer hidden neurons and with less need for regularisation. Our Global-Local Artificial Neural Network (GL-ANN) is also seen to compare favourably with both Perceptron Radial Basis Net (PRBFN) and Regression Tree RBFsen
dc.language.isoenen
dc.publisherSpringeren
dc.relation.urlhttp://www.springerlink.com/content/105633/en
dc.titleA global-local artificial neural network with application to wave overtopping predictionen
dc.typeBook chapteren
dc.identifier.eissn1611-3349-
All Items in e-space are protected by copyright, with all rights reserved, unless otherwise indicated.