ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods

Schlegel, Udo; Cakmak, Eren; Keim, Daniel A.

ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods

Dateien

Schlegel_2-qm5kpmaxjly15.pdfGröße: 287.22 KBDownloads: 202

Datum

2020

Angaben zur Forschungsförderung

Deutsche Forschungsgemeinschaft (DFG): 422037984
European Union (EU): 830892

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft
Exzellenzcluster "Centre for the Advanced Study of Collective Behaviour"

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

ARCHAMBAULT, Daniel, Hrsg. und andere. Machine Learning Methods in Visualisation for Big Data 2020. Genf: The Eurographics Association, 2020, S. 7-11. ISBN 978-3-03868-113-7. Verfügbar unter: doi: 10.2312/mlvis.20201100

Zusammenfassung

Explainable artificial intelligence (XAI) methods aim to reveal the non-transparent decision-making mechanisms of black-box models. The evaluation of insight generated by such XAI methods remains challenging as the applied techniques depend on many factors (e.g., parameters and human interpretation). We propose ModelSpeX, a visual analytics workflow to interactively extract human-centered rule-sets to generate model specifications from black-box models (e.g., neural networks). The workflow enables to reason about the underlying problem, to extract decision rule sets, and to evaluate the suitability of the model for a particular task. An exemplary usage scenario walks an analyst trough the steps of the workflow to show the applicability.

Fachgebiet (DDC)

004 Informatik

Konferenz

International Workshop on Machine Learning in Visualisation for Big Data : MLVis 2020, 25. Mai 2020 - 29. Mai 2020, Norrköping, Sweden

Zitieren

ISO 690

SCHLEGEL, Udo, Eren CAKMAK, Daniel A. KEIM, 2020. ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods. International Workshop on Machine Learning in Visualisation for Big Data : MLVis 2020. Norrköping, Sweden, 25. Mai 2020 - 29. Mai 2020. In: ARCHAMBAULT, Daniel, Hrsg. und andere. Machine Learning Methods in Visualisation for Big Data 2020. Genf: The Eurographics Association, 2020, S. 7-11. ISBN 978-3-03868-113-7. Verfügbar unter: doi: 10.2312/mlvis.20201100

BibTex

@inproceedings{Schlegel2020Model-49721,
  year={2020},
  doi={10.2312/mlvis.20201100},
  title={ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods},
  isbn={978-3-03868-113-7},
  publisher={The Eurographics Association},
  address={Genf},
  booktitle={Machine Learning Methods in Visualisation for Big Data 2020},
  pages={7--11},
  editor={Archambault, Daniel},
  author={Schlegel, Udo and Cakmak, Eren 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/123456789/49721">
    <dcterms:title>ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:language>eng</dc:language>
    <dcterms:abstract xml:lang="eng">Explainable artificial intelligence (XAI) methods aim to reveal the non-transparent decision-making mechanisms of black-box models. The evaluation of insight generated by such XAI methods remains challenging as the applied techniques depend on many factors (e.g., parameters and human interpretation). We propose ModelSpeX, a visual analytics workflow to interactively extract human-centered rule-sets to generate model specifications from black-box models (e.g., neural networks). The workflow enables to reason about the underlying problem, to extract decision rule sets, and to evaluate the suitability of the model for a particular task. An exemplary usage scenario walks an analyst trough the steps of the workflow to show the applicability.</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-05-28T10:03:28Z</dcterms:available>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49721/1/Schlegel_2-qm5kpmaxjly15.pdf"/>
    <dc:creator>Cakmak, Eren</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:creator>Schlegel, Udo</dc:creator>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49721/1/Schlegel_2-qm5kpmaxjly15.pdf"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/>
    <dc:contributor>Schlegel, Udo</dc:contributor>
    <dcterms:issued>2020</dcterms:issued>
    <dc:contributor>Cakmak, Eren</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-05-28T10:03:28Z</dc:date>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/49721"/>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja