Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/3001
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tsapatsoulis, Nicolas | en |
dc.contributor.author | Wallace, Manolis | en |
dc.contributor.author | Kasderidis, Stathis | en |
dc.contributor.other | Τσαπατσούλης, Νικόλας | - |
dc.date.accessioned | 2009-05-27T10:50:28Z | en |
dc.date.accessioned | 2013-05-16T14:08:45Z | - |
dc.date.accessioned | 2015-12-02T12:30:06Z | - |
dc.date.available | 2009-05-27T10:50:28Z | en |
dc.date.available | 2013-05-16T14:08:45Z | - |
dc.date.available | 2015-12-02T12:30:06Z | - |
dc.date.issued | 2003 | en |
dc.identifier.citation | Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003, p.173 | en |
dc.identifier.isbn | 9783540404088 | en |
dc.identifier.uri | https://hdl.handle.net/20.500.14279/3001 | - |
dc.description | ICANN/ICONIP 2003,(2003,Istanbul,Turkey) | en |
dc.description.abstract | Adaptivity to non-stationary contexts is a very important property for intelligent systems in general, as well as to a variety of applications of knowledge based systems in era of “ambient intelligence”. In this paper we present a modified Resource Allocating Network architecture that allows for online adaptation and knowledge modelling through its adaptive structure. As in any neural network system proper parameter initialization reduces training time and effort. However, in RAN architectures, proper parameter initialization also leads to compact modelling (less hidden nodes) of the process under examination, and consequently to better generalization. In the cases of high-dimensional data parameter initialization is both difficult and time consuming. In the proposed scheme a high – dimensional, unsupervised clustering method is used to properly initialize the RAN architecture. Clusters correspond to the initial nodes of RAN, while output layer weights are also extracted from the clustering procedure. The efficiency of the proposed method has been tested on several classes of publicly available data (iris, ionosphere, etc.) | en |
dc.format | en | |
dc.language.iso | en | en |
dc.relation.ispartofseries | Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003; | en |
dc.rights | © Springer | en |
dc.subject | Neural networks (Computer science)--Congresses | en |
dc.title | Improving the Performance of Resource Allocation Networks through Hierarchical Clustering of High-Dimensional Data | en |
dc.type | Book Chapter | en |
dc.collaboration | National Technical University Of Athens | - |
dc.collaboration | King's College London | - |
dc.country | Greece | - |
dc.country | United Kingdom | - |
dc.identifier.doi | 10.1007/3-540-44989-2_22 | en |
dc.dept.handle | 123456789/54 | en |
item.fulltext | With Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_3248 | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
item.openairetype | bookPart | - |
item.grantfulltext | open | - |
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: | Κεφάλαια βιβλίων/Book chapters |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Tsapatsoulis_Improving the Performance of Resource.pdf | 115.04 kB | Adobe PDF | View/Open |
CORE Recommender
SCOPUSTM
Citations
50
3
checked on Nov 8, 2023
Page view(s) 20
498
Last Week
2
2
Last month
2
2
checked on Sep 4, 2024
Download(s) 50
537
checked on Sep 4, 2024
Google ScholarTM
Check
Altmetric
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.