Showing the Equivalence of Two Training Algorithms - Part II

Fischer, Ingrid; Koch, Manuel; Berthold, Michael R.

Showing the Equivalence of Two Training Algorithms - Part II

Files

There are no files associated with this item.

Date

1998

Authors

Fischer, Ingrid

Koch, Manuel

Berthold, Michael R.

Publication type

Contribution to a conference collection

Published in

1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227). - IEEE, 1998. - pp. 452-456. - ISBN 0-7803-4859-1

Abstract

In previous work Graph Transformations have been shown to offer a powerful way to formally specify Neural Networks and their corresponding training algorithms. It has also been shown how to use this formalism to prove properties of the used algorithms. In this paper Graph Transformations are used to show the equivalence of two training algorithms for Recurrent Neural Networks, Back Propagation Through Time and a variant of Real Time Backpropagation. In addition to this proof a whole class of related training algorithm emerges from the used formalism. In part I of this paper the formalization of the two algorithms is shown; part II then shows how Graph Transformations can be used to prove the equivalence of both algorithms.

Subject (DDC)

004 Computer Science

Conference

ICNN '98 - International Conference on Neural Networks, Anchorage, AK, USA

Cite This

ISO 690

FISCHER, Ingrid, Manuel KOCH, Michael R. BERTHOLD, 1998. Showing the Equivalence of Two Training Algorithms - Part II. 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, pp. 452-456. ISBN 0-7803-4859-1. Available under: doi: 10.1109/IJCNN.1998.682309

BibTex

@inproceedings{Fischer1998Showi-24289,
  year={1998},
  doi={10.1109/IJCNN.1998.682309},
  title={Showing the Equivalence of Two Training Algorithms - Part II},
  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={452--456},
  author={Fischer, Ingrid and Koch, Manuel and Berthold, Michael R.}
}

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/123456789/24289">
    <dc:rights>terms-of-use</dc:rights>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <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. 452-456. - ISBN 0-7803-4859-1</dcterms:bibliographicCitation>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-08-22T08:03:12Z</dcterms:available>
    <dcterms:issued>1998</dcterms:issued>
    <dc:contributor>Fischer, Ingrid</dc:contributor>
    <dc:language>eng</dc:language>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-08-22T08:03:12Z</dc:date>
    <dc:contributor>Koch, Manuel</dc:contributor>
    <dcterms:abstract xml:lang="eng">In previous work Graph Transformations have been shown to offer a powerful way to formally specify Neural Networks and their corresponding training algorithms. It has also been shown how to use this formalism to prove properties of the used algorithms. In this paper Graph Transformations are used to show the equivalence of two training algorithms for Recurrent Neural Networks, Back Propagation Through Time and a variant of Real Time Backpropagation. In addition to this proof a whole class of related training algorithm emerges from the used formalism. In part I of this paper the formalization of the two algorithms is shown; part II then shows how Graph Transformations can be used to prove the equivalence of both algorithms.</dcterms:abstract>
    <dc:creator>Fischer, Ingrid</dc:creator>
    <dc:creator>Koch, Manuel</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/24289"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Berthold, Michael R.</dc:contributor>
    <dcterms:title>Showing the Equivalence of Two Training Algorithms - Part II</dcterms:title>
    <dc:creator>Berthold, Michael R.</dc:creator>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

No