Publikation:

Boosting the Performance of RBF Networks with Dynamic Decay Adjustment

Lade...
Vorschaubild

Dateien

BeDi95_dda_nips7.pdf
BeDi95_dda_nips7.pdfGröße: 197.23 KBDownloads: 173

Datum

1995

Autor:innen

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

DOI (zitierfähiger Link)
ArXiv-ID

Internationale Patentnummer

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published

Erschienen in

TESAURO, G., ed. and others. Advances in Neural Information Processing Systems 7 (NIPS 1994). 1995

Zusammenfassung

Radial Basis Function (RBF) Networks, also known as networks of locally-tuned processing units (see [6]) are well known for their ease of use. Most algorithms used to train these types of networks, however, require a fxed architecture, in which the number of units in the hidden layer must be determined before training starts. The RCE training algorithm, introduced by Reilly, Cooper and Elbaum (see [8]), and its probabilistic extension, the P-RCE algorithm, take advantage of a growing structure in which hidden units are only introduced when necessary. The nature of these algorithms allows training to reach stability much faster than is the case for gradient-descent based methods. Unfortunately P-RCE networks do not adjust the standard deviation of their prototypes individually, using only one global value for this parameter. This paper introduces the Dynamic Decay Adjustment (DDA) algorithm which utilizes the constructive nature of the P-RCE algorithm together with independent adaptation of each prototype's decay factor. In addition, this radial adjustment is class dependent and distinguishes between different neighbours. It is shown that networks trained with the presented algorithm perform substantially better than common RBF networks.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Konferenz

Advances in Neural Information Processing Systems 7 (NIPS 1994)
Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690BERTHOLD, Michael R., Jay DIAMOND, 1995. Boosting the Performance of RBF Networks with Dynamic Decay Adjustment. Advances in Neural Information Processing Systems 7 (NIPS 1994). In: TESAURO, G., ed. and others. Advances in Neural Information Processing Systems 7 (NIPS 1994). 1995
BibTex
@inproceedings{Berthold1995Boost-5427,
  year={1995},
  title={Boosting the Performance of RBF Networks with Dynamic Decay Adjustment},
  url={https://proceedings.neurips.cc/paper/1994/hash/c8c41c4a18675a74e01c8a20e8a0f662-Abstract.html},
  booktitle={Advances in Neural Information Processing Systems 7 (NIPS 1994)},
  editor={Tesauro, G.},
  author={Berthold, Michael R. and Diamond, Jay}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/5427">
    <dc:contributor>Berthold, Michael R.</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:title>Boosting the Performance of RBF Networks with Dynamic Decay Adjustment</dcterms:title>
    <dc:language>eng</dc:language>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-03-24T15:55:18Z</dc:date>
    <dcterms:issued>1995</dcterms:issued>
    <dc:format>application/pdf</dc:format>
    <dc:creator>Berthold, Michael R.</dc:creator>
    <dcterms:abstract xml:lang="eng">Radial Basis Function (RBF) Networks, also known as networks of locally-tuned processing units (see [6]) are well known for their ease of use. Most algorithms used to train these types of networks, however, require a fxed architecture, in which the number of units in the hidden layer must be determined before training starts. The RCE training algorithm, introduced by Reilly, Cooper and Elbaum (see [8]), and its probabilistic extension, the P-RCE algorithm, take advantage of a growing structure in which hidden units are only introduced when necessary. The nature of these algorithms allows training to reach stability much faster than is the case for gradient-descent based methods. Unfortunately P-RCE networks do not adjust the standard deviation of their prototypes individually, using only one global value for this parameter. This paper introduces the Dynamic Decay Adjustment (DDA) algorithm which utilizes the constructive nature of the P-RCE algorithm together with independent adaptation of each prototype's decay factor. In addition, this radial adjustment is class dependent and distinguishes between different neighbours. It is shown that networks trained with the presented algorithm perform substantially better than common RBF networks.</dcterms:abstract>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/5427"/>
    <dcterms:bibliographicCitation>First publ. in: Advances in Neural Information Processing 7 (1995), pp. 8</dcterms:bibliographicCitation>
    <dc:rights>Attribution-NonCommercial-NoDerivs 2.0 Generic</dc:rights>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/5427/1/BeDi95_dda_nips7.pdf"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-03-24T15:55:18Z</dcterms:available>
    <dc:creator>Diamond, Jay</dc:creator>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/5427/1/BeDi95_dda_nips7.pdf"/>
    <dc:contributor>Diamond, Jay</dc:contributor>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-nd/2.0/"/>
  </rdf:Description>
</rdf:RDF>

Interner Vermerk

xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter

Kontakt

Prüfungsdatum der Dissertation

Finanzierungsart

Kommentar zur Publikation

Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
Begutachtet
Diese Publikation teilen