Visualization-Assisted Development of Deep Learning Models in Offline Handwriting Recognition

Lade...
Vorschaubild
Dateien
Schall_2-1prqtf0ga5nfs7.pdf
Schall_2-1prqtf0ga5nfs7.pdfGröße: 322.83 KBDownloads: 235
Datum
2018
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
Symposium on Visualization in Data Science (VDS) at IEEE VIS 2018. 2018
Zusammenfassung

Deep learning is a field of machine learning that has been the focus of active research and successful applications in recent years. Offline handwriting recognition is one of the research fields and applications were deep neural networks have shown high accuracy. Deep learning models and their training pipeline show a large amount of hyper-parameters in their data selection, transformation, network topology and training process that are sometimes interdependent. This increases the overall difficulty and time necessary for building and training a model for a specific data set and task at hand. This work proposes a novel visualization-assisted workflow that guides the model developer through the hyper-parameter search in order to identify relevant parameters and modify them in a meaningful way. This decreases the overall time necessary for building and training a model. The contributions of this work are a workflow for hyper-parameter search in offline handwriting recognition and a heat map based visualization technique for deep neural networks in multi-line offline handwriting recognition. This work applies to offline handwriting recognition, but the general workflow can possibly be adapted to other tasks as well.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Symposium on Visualization in Data Science (VDS) at IEEE VIS 2018, 22. Okt. 2018, Berlin
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690SCHALL, Martin, Dominik SACHA, Manuel STEIN, Matthias O. FRANZ, Daniel A. KEIM, 2018. Visualization-Assisted Development of Deep Learning Models in Offline Handwriting Recognition. Symposium on Visualization in Data Science (VDS) at IEEE VIS 2018. Berlin, 22. Okt. 2018. In: Symposium on Visualization in Data Science (VDS) at IEEE VIS 2018. 2018
BibTex
@inproceedings{Schall2018Visua-45050,
  year={2018},
  title={Visualization-Assisted Development of Deep Learning Models in Offline Handwriting Recognition},
  url={https://scibib.dbvis.de/publications/view/773},
  booktitle={Symposium on Visualization in Data Science (VDS) at IEEE VIS 2018},
  author={Schall, Martin and Sacha, Dominik and Stein, Manuel and Franz, Matthias O. and Keim, Daniel A.}
}
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/123456789/45050">
    <dc:contributor>Franz, Matthias O.</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45050/1/Schall_2-1prqtf0ga5nfs7.pdf"/>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:issued>2018</dcterms:issued>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dc:creator>Franz, Matthias O.</dc:creator>
    <dc:language>eng</dc:language>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/45050"/>
    <dc:creator>Schall, Martin</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-14T15:31:24Z</dc:date>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-14T15:31:24Z</dcterms:available>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45050/1/Schall_2-1prqtf0ga5nfs7.pdf"/>
    <dc:contributor>Schall, Martin</dc:contributor>
    <dc:contributor>Sacha, Dominik</dc:contributor>
    <dcterms:abstract xml:lang="eng">Deep learning is a field of machine learning that has been the focus of active research and successful applications in recent years. Offline handwriting recognition is one of the research fields and applications were deep neural networks have shown high accuracy. Deep learning models and their training pipeline show a large amount of hyper-parameters in their data selection, transformation, network topology and training process that are sometimes interdependent. This increases the overall difficulty and time necessary for building and training a model for a specific data set and task at hand. This work proposes a novel visualization-assisted workflow that guides the model developer through the hyper-parameter search in order to identify relevant parameters and modify them in a meaningful way. This decreases the overall time necessary for building and training a model. The contributions of this work are a workflow for hyper-parameter search in offline handwriting recognition and a heat map based visualization technique for deep neural networks in multi-line offline handwriting recognition. This work applies to offline handwriting recognition, but the general workflow can possibly be adapted to other tasks as well.</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Sacha, Dominik</dc:creator>
    <dc:contributor>Stein, Manuel</dc:contributor>
    <dcterms:title>Visualization-Assisted Development of Deep Learning Models in Offline Handwriting Recognition</dcterms:title>
    <dc:creator>Stein, Manuel</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
Prüfdatum der URL
2019-02-14
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen