Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/1956
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wallace, Manolis | - |
dc.contributor.author | Tsapatsoulis, Nicolas | - |
dc.contributor.author | Kollias, Stefanos D. | - |
dc.date.accessioned | 2009-05-26T07:51:18Z | en |
dc.date.accessioned | 2013-05-16T13:11:03Z | - |
dc.date.accessioned | 2015-12-02T09:41:17Z | - |
dc.date.available | 2009-05-26T07:51:18Z | en |
dc.date.available | 2013-05-16T13:11:03Z | - |
dc.date.available | 2015-12-02T09:41:17Z | - |
dc.date.issued | 2004 | - |
dc.identifier.citation | Neural Networks, 2004, Vol. 18, no. 2, pp. 117-122 | en_US |
dc.identifier.issn | 08936080 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.14279/1956 | - |
dc.description.abstract | In any neural network system, proper parameter initialization reduces training time and effort, and generally leads to compact modeling of the process under examination, i.e. less complex network structures and better generalization. However, in cases of multi-dimensional data, parameter initialization is both difficult and time consuming. In the proposed scheme a novel, multi-dimensional, unsupervised clustering method is used to properly initialize neural network architectures, focusing on resource allocating networks (RAN); both the hidden and output layer parameters are determined by the output of the clustering process, without the need for any user interference. The main contribution of this work is that the proposed approach leads to network structures that are compact, efficient and achieve best classification results, without the need for manual selection of suitable initial network parameters. The efficiency of the proposed method has been tested on several classes of publicly available data, such as iris, Wisconsin and ionosphere data. | en_US |
dc.format | en_US | |
dc.language.iso | en | en_US |
dc.relation.ispartof | Neural Networks | en_US |
dc.rights | © Elsevier | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | * |
dc.subject | Wisconsin | en_US |
dc.subject | Ionosphere | en_US |
dc.subject | Resource allocating networks | en_US |
dc.title | Intelligent initialization of resource allocating RBF networks | en_US |
dc.type | Article | en_US |
dc.link | 10.1016/j.neunet.2004.11.005 | en_US |
dc.collaboration | University of Indianapolis | en_US |
dc.collaboration | National Technical University Of Athens | en_US |
dc.subject.category | ENGINEERING AND TECHNOLOGY | en_US |
dc.journals | Subscription | en_US |
dc.country | Greece | en_US |
dc.subject.field | Engineering and Technology | en_US |
dc.publication | Peer Reviewed | en_US |
dc.dept.handle | 123456789/54 | en |
dc.relation.issue | 2 | en_US |
dc.relation.volume | 18 | en_US |
cut.common.academicyear | 2003-2004 | en_US |
dc.identifier.spage | 117 | en_US |
dc.identifier.epage | 122 | en_US |
item.grantfulltext | none | - |
item.openairecristype | http://purl.org/coar/resource_type/c_6501 | - |
item.fulltext | No Fulltext | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
item.openairetype | article | - |
crisitem.journal.journalissn | 0893-6080 | - |
crisitem.journal.publisher | Elsevier | - |
crisitem.author.dept | Department of Communication and Marketing | - |
crisitem.author.faculty | Faculty of Communication and Media Studies | - |
crisitem.author.orcid | 0000-0002-6739-8602 | - |
crisitem.author.parentorg | Faculty of Communication and Media Studies | - |
Appears in Collections: | Άρθρα/Articles |
CORE Recommender
This item is licensed under a Creative Commons License