Formalizing neural networks using graph transformations

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

BERTHOLD, Michael, Ingrid FISCHER, 1997. Formalizing neural networks using graph transformations. International Conference on Neural Networks (ICNN'97). Houston, TX, USA. In: Proceedings of International Conference on Neural Networks (ICNN'97). IEEE, pp. 275-280. ISBN 0-7803-4122-8. Available under: doi: 10.1109/ICNN.1997.611678

@inproceedings{Berthold1997Forma-24285, title={Formalizing neural networks using graph transformations}, year={1997}, doi={10.1109/ICNN.1997.611678}, isbn={0-7803-4122-8}, publisher={IEEE}, booktitle={Proceedings of International Conference on Neural Networks (ICNN'97)}, pages={275--280}, author={Berthold, Michael and Fischer, Ingrid} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dspace:isPartOfCollection rdf:resource=""/> <dcterms:bibliographicCitation>The 1997 IEEE International Conference on Neural Networks : June 9-12, 1997, Westin Galleria Hotel, Houston, Texas, USA; Vol. 1 / [Nicolaos B. Karayiannis, general chair]. - Piscataway, NJ : IEEE Service Center, 1997. - S. 275-280. - ISBN 0-7803-4122-8</dcterms:bibliographicCitation> <dc:creator>Fischer, Ingrid</dc:creator> <dc:contributor>Berthold, Michael</dc:contributor> <dc:contributor>Fischer, Ingrid</dc:contributor> <dc:date rdf:datatype="">2013-08-20T14:13:23Z</dc:date> <dcterms:title>Formalizing neural networks using graph transformations</dcterms:title> <dcterms:rights rdf:resource=""/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:isPartOf rdf:resource=""/> <dc:rights>terms-of-use</dc:rights> <dcterms:issued>1997</dcterms:issued> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <bibo:uri rdf:resource=""/> <dcterms:available rdf:datatype="">2013-08-20T14:13:23Z</dcterms:available> <dc:creator>Berthold, Michael</dc:creator> <dc:language>eng</dc:language> <dcterms:abstract xml:lang="eng">In this paper a unifying framework for the formalization of different types of neural networks and the corresponding algorithms for computation and training is presented. The used graph transformation system offers a formalism to verify properties of the networks and their algorithms. In addition the presented methodology can be used as a tool to visualize and design different types of networks along with all required algorithms. An algorithm that adapts network parameters using standard gradient descent as well as parts of a constructive, topology-changing algorithm for probabilistic neural networks are used to demonstrate the proposed formalism.</dcterms:abstract> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


My Account