Connectionist Taxonomy Learning
Connectionist Taxonomy Learning
View/Type of Scholarly Publication
DissertationDate of Exam
03.05.2007Date of Publication
2007Advisor
Lenders, WinfriedCo-Referee
Schade, UlrichMetadata
Show full item record
Citable Links 
Abstract
The thesis presents an unsupervised connectionist network using spreading activation mechanism. By means of self-organization, the network is capable of creating a taxonomy of concepts which serves as a backbone for a respective ontology. The system is a biologically inspired constructivist hybrid between connectionist networks using distributed and localist data representation. Unlike most currently developed models it is capable to deal with analog signals and displays cognitive properties of categorization process. The thesis presents the general overview over the system’s architecture and method of network build-up and shows results of several experiments exploring the nature of categorization performed with the use of the described network.
Subjects
Konnektionismus, semantisches Netzwerk, Taxonomie, Kategorisierung
Classification (DDC)
400 Sprache, LinguistikFrey, Miłosław L.: Connectionist Taxonomy Learning. - Bonn, 2007. - Dissertation, Rheinische Friedrich-Wilhelms-Universität Bonn.
Online-Ausgabe in bonndoc: https://nbn-resolving.org/urn:nbn:de:hbz:5-11913
Online-Ausgabe in bonndoc: https://nbn-resolving.org/urn:nbn:de:hbz:5-11913
@phdthesis{handle:20.500.11811/2766,
urn: https://nbn-resolving.org/urn:nbn:de:hbz:5-11913,
author = {{Miłosław L. Frey}},
title = {Connectionist Taxonomy Learning},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
year = 2007,
note = {The thesis presents an unsupervised connectionist network using spreading activation mechanism. By means of self-organization, the network is capable of creating a taxonomy of concepts which serves as a backbone for a respective ontology. The system is a biologically inspired constructivist hybrid between connectionist networks using distributed and localist data representation. Unlike most currently developed models it is capable to deal with analog signals and displays cognitive properties of categorization process. The thesis presents the general overview over the system’s architecture and method of network build-up and shows results of several experiments exploring the nature of categorization performed with the use of the described network.},
url = {https://hdl.handle.net/20.500.11811/2766}
}
urn: https://nbn-resolving.org/urn:nbn:de:hbz:5-11913,
author = {{Miłosław L. Frey}},
title = {Connectionist Taxonomy Learning},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
year = 2007,
note = {The thesis presents an unsupervised connectionist network using spreading activation mechanism. By means of self-organization, the network is capable of creating a taxonomy of concepts which serves as a backbone for a respective ontology. The system is a biologically inspired constructivist hybrid between connectionist networks using distributed and localist data representation. Unlike most currently developed models it is capable to deal with analog signals and displays cognitive properties of categorization process. The thesis presents the general overview over the system’s architecture and method of network build-up and shows results of several experiments exploring the nature of categorization performed with the use of the described network.},
url = {https://hdl.handle.net/20.500.11811/2766}
}
The following license files are associated with this item:
