Showing the Equivalence of Two Training Algorithms, I
| dc.contributor.author | Koch, Manuel | deu |
| dc.contributor.author | Fischer, Ingrid | deu |
| dc.contributor.author | Berthold, Michael R. | |
| dc.date.accessioned | 2013-08-22T08:22:22Z | deu |
| dc.date.available | 2013-08-22T08:22:22Z | deu |
| dc.date.issued | 1998 | |
| dc.description.abstract | Graph transformations offer a powerful way to formally specify neural networks and their corresponding training algorithms. This formalism can be used to prove properties of these algorithms. In this paper graph transformations are used to show the equivalence of two training algorithms for recurrent neural networks; backpropagation through time, and a variant of real-time backpropagation. In addition to this proof a whole class of related training algorithms emerges from the used formalism. | eng |
| dc.description.version | published | |
| dc.identifier.citation | The 1998 IEEE International Joint Conference on Neural Networks Proceedings : IEEE World Congress on Computational Intelligence : May 4-May 9, 1998, Anchorage, Alaska, USA / [general chair: Patrick K. Simpson]. Piscataway : IEEE Service Center, 1998. - S. 447-456. - ISBN 0-7803-4859-1 | deu |
| dc.identifier.doi | 10.1109/IJCNN.1998.682308 | deu |
| dc.identifier.uri | http://kops.uni-konstanz.de/handle/123456789/24290 | |
| dc.language.iso | eng | deu |
| dc.legacy.dateIssued | 2013-08-22 | deu |
| dc.rights | terms-of-use | deu |
| dc.rights.uri | https://rightsstatements.org/page/InC/1.0/ | deu |
| dc.subject.ddc | 004 | deu |
| dc.title | Showing the Equivalence of Two Training Algorithms, I | eng |
| dc.type | INPROCEEDINGS | deu |
| dspace.entity.type | Publication | |
| kops.citation.bibtex | @inproceedings{Koch1998Showi-24290,
year={1998},
doi={10.1109/IJCNN.1998.682308},
title={Showing the Equivalence of Two Training Algorithms, I},
isbn={0-7803-4859-1},
publisher={IEEE},
booktitle={1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)},
pages={447--456},
author={Koch, Manuel and Fischer, Ingrid and Berthold, Michael R.}
} | |
| kops.citation.iso690 | KOCH, Manuel, Ingrid FISCHER, Michael R. BERTHOLD, 1998. Showing the Equivalence of Two Training Algorithms, I. ICNN '98 - International Conference on Neural Networks. Anchorage, AK, USA. In: 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227). IEEE, 1998, pp. 447-456. ISBN 0-7803-4859-1. Available under: doi: 10.1109/IJCNN.1998.682308 | deu |
| kops.citation.iso690 | KOCH, Manuel, Ingrid FISCHER, Michael R. BERTHOLD, 1998. Showing the Equivalence of Two Training Algorithms, I. ICNN '98 - International Conference on Neural Networks. Anchorage, AK, USA. In: 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227). IEEE, 1998, pp. 447-456. ISBN 0-7803-4859-1. Available under: doi: 10.1109/IJCNN.1998.682308 | eng |
| kops.citation.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/123456789/24290">
<dc:rights>terms-of-use</dc:rights>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-08-22T08:22:22Z</dc:date>
<dcterms:issued>1998</dcterms:issued>
<dc:creator>Fischer, Ingrid</dc:creator>
<dc:creator>Berthold, Michael R.</dc:creator>
<bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/24290"/>
<dcterms:title>Showing the Equivalence of Two Training Algorithms, I</dcterms:title>
<dc:contributor>Koch, Manuel</dc:contributor>
<dc:contributor>Fischer, Ingrid</dc:contributor>
<dc:creator>Koch, Manuel</dc:creator>
<dcterms:abstract xml:lang="eng">Graph transformations offer a powerful way to formally specify neural networks and their corresponding training algorithms. This formalism can be used to prove properties of these algorithms. In this paper graph transformations are used to show the equivalence of two training algorithms for recurrent neural networks; backpropagation through time, and a variant of real-time backpropagation. In addition to this proof a whole class of related training algorithms emerges from the used formalism.</dcterms:abstract>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:language>eng</dc:language>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<dc:contributor>Berthold, Michael R.</dc:contributor>
<dcterms:bibliographicCitation>The 1998 IEEE International Joint Conference on Neural Networks Proceedings : IEEE World Congress on Computational Intelligence : May 4-May 9, 1998, Anchorage, Alaska, USA / [general chair: Patrick K. Simpson]. Piscataway : IEEE Service Center, 1998. - S. 447-456. - ISBN 0-7803-4859-1</dcterms:bibliographicCitation>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-08-22T08:22:22Z</dcterms:available>
</rdf:Description>
</rdf:RDF> | |
| kops.conferencefield | ICNN '98 - International Conference on Neural Networks, Anchorage, AK, USA | deu |
| kops.flag.knbibliography | false | |
| kops.identifier.nbn | urn:nbn:de:bsz:352-242907 | deu |
| kops.location.conference | Anchorage, AK, USA | |
| kops.sourcefield | <i>1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)</i>. IEEE, 1998, pp. 447-456. ISBN 0-7803-4859-1. Available under: doi: 10.1109/IJCNN.1998.682308 | deu |
| kops.sourcefield.plain | 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227). IEEE, 1998, pp. 447-456. ISBN 0-7803-4859-1. Available under: doi: 10.1109/IJCNN.1998.682308 | deu |
| kops.sourcefield.plain | 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227). IEEE, 1998, pp. 447-456. ISBN 0-7803-4859-1. Available under: doi: 10.1109/IJCNN.1998.682308 | eng |
| kops.submitter.email | christoph.petzmann@uni-konstanz.de | deu |
| kops.title.conference | ICNN '98 - International Conference on Neural Networks | |
| relation.isAuthorOfPublication | 56ea9ab6-14a4-493e-8ef1-3c064e0c50a1 | |
| relation.isAuthorOfPublication.latestForDiscovery | 56ea9ab6-14a4-493e-8ef1-3c064e0c50a1 | |
| source.bibliographicInfo.fromPage | 447 | |
| source.bibliographicInfo.toPage | 456 | |
| source.identifier.isbn | 0-7803-4859-1 | |
| source.publisher | IEEE | |
| source.title | 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227) |
Dateien
Lizenzbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- license.txt
- Größe:
- 1.92 KB
- Format:
- Plain Text
- Beschreibung:
