A probabilistic extension for the DDA algorithm

Zitieren

Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

BERTHOLD, Michael, 1996. A probabilistic extension for the DDA algorithm. International Conference on Neural Networks (ICNN'96). Washington, DC, USA. In: Proceedings of International Conference on Neural Networks (ICNN'96). International Conference on Neural Networks (ICNN'96). Washington, DC, USA. IEEE, pp. 341-346. ISBN 0-7803-3210-5

@inproceedings{Berthold1996proba-24207, title={A probabilistic extension for the DDA algorithm}, year={1996}, doi={10.1109/ICNN.1996.548915}, isbn={0-7803-3210-5}, publisher={IEEE}, booktitle={Proceedings of International Conference on Neural Networks (ICNN'96)}, pages={341--346}, author={Berthold, Michael} }

<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/24207"> <dc:creator>Berthold, Michael</dc:creator> <dcterms:bibliographicCitation>The 1996 IEEE international conference on neural networks, June 3-6, 1996, Sheraton Washington Hotel, Washington, DC, USA; Vol. 1 / [Benjamin W. Wah, general chair]. - Piscataway, NJ : IEEE Service Center, 1996. - S. 341-346. - ISBN 0-7803-3210-5</dcterms:bibliographicCitation> <dcterms:rights rdf:resource="http://nbn-resolving.org/urn:nbn:de:bsz:352-20140905103605204-4002607-1"/> <dcterms:abstract xml:lang="eng">Many algorithms to train radial basis function (RBF) networks have already been proposed. Most of them, however, concentrate on building function approximators and only few specialized algorithms are known that concentrate on RBFs for classification. They are based on heuristics that focus on finding areas where relatively few (or no) conflicts occur, but do not try to approximate the underlying probability distribution function (PDF) of the data. In this paper an extension for an already existing constructive algorithm for RBF networks is introduced. The new method uses the dynamic decay adjustment (DDA) algorithm to find conflict free areas and builds more appropriate PDFs inside each such zone. On a dataset which was generated using Gaussian distributions it is demonstrated that this method builds almost optimal classifiers that compare very well with the theoretical Bayes classifier. It is shown, however, that the generalization capability of such networks does not compare favourable to the DDA itself.</dcterms:abstract> <dcterms:title>A probabilistic extension for the DDA algorithm</dcterms:title> <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/24207"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-08-23T13:19:00Z</dc:date> <dcterms:issued>1996</dcterms:issued> <dc:rights>deposit-license</dc:rights> <dc:language>eng</dc:language> <dc:contributor>Berthold, Michael</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-08-23T13:19:00Z</dcterms:available> </rdf:Description> </rdf:RDF>

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto