Self-Organizing Neural Networks for Sequence Processing

Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://osnadocs.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-2005012711
Open Access logo originally created by the Public Library of Science (PLoS)
Langanzeige der Metadaten
DC ElementWertSprache
dc.contributor.advisorProf. Dr. Barbara Hammer
dc.creatorStrickert, Marc
dc.date.accessioned2010-01-30T14:50:34Z
dc.date.available2010-01-30T14:50:34Z
dc.date.issued2005-01-27T19:13:25Z
dc.date.submitted2005-01-27T19:13:25Z
dc.identifier.urihttps://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-2005012711-
dc.description.abstractThis work investigates the self-organizing representation of temporal data in prototype-based neural networks. Extensions of the supervised learning vector quantization (LVQ) and the unsupervised self-organizing map (SOM) are considered in detail. The principle of Hebbian learning through prototypes yields compact data models that can be easily interpreted by similarity reasoning. In order to obtain a robust prototype dynamic, LVQ is extended by neighborhood cooperation between neurons to prevent a strong dependence on the initial prototype locations. Additionally, implementations of more general, adaptive metrics are studied with a particular focus on the built-in detection of data attributes involved for a given classifcation task. For unsupervised sequence processing, two modifcations of SOM are pursued: the SOM for structured data (SOMSD) realizing an efficient back-reference to the previous best matching neuron in a triangular low-dimensional neural lattice, and the merge SOM (MSOM) expressing the temporal context as a fractal combination of the previously most active neuron and its context. The first SOMSD extension tackles data dimension reduction and planar visualization, the second MSOM is designed for obtaining higher quantization accuracy. The supplied experiments underline the data modeling quality of the presented methods.eng
dc.language.isoeng
dc.subjectvector quantization
dc.subjectself-organization
dc.subjectrelevance learning
dc.subjectclassification
dc.subjectclustering
dc.subjectsequence processing
dc.subjectcontext
dc.subjectfractal representation
dc.subjectMSOM
dc.subject.ddc000 - Informatik, Wissen, Systeme
dc.titleSelf-Organizing Neural Networks for Sequence Processingeng
dc.typeDissertation oder Habilitation [doctoralThesis]-
thesis.locationOsnabrück-
thesis.institutionUniversität-
thesis.typeDissertation [thesis.doctoral]-
thesis.date2004-01-14T12:00:00Z-
elib.elibid384-
elib.marc.edtfangmeier-
elib.dct.accessRightsa-
elib.dct.created2005-01-18T11:46:09Z-
elib.dct.modified2005-01-27T19:13:25Z-
dc.contributor.refereeProf. Dr. Helge Ritter
dc.subject.dnb28 - Informatik, Datenverarbeitungger
vCard.ORGFB6ger
Enthalten in den Sammlungen:FB06 - E-Dissertationen

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
E-Diss384_thesis.pdfPräsentationsformat1,62 MBAdobe PDF
E-Diss384_thesis.pdf
Miniaturbild
Öffnen/Anzeigen


Alle Ressourcen im Repositorium osnaDocs sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt. rightsstatements.org