ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods
| dc.contributor.author | Schlegel, Udo | |
| dc.contributor.author | Cakmak, Eren | |
| dc.contributor.author | Keim, Daniel A. | |
| dc.date.accessioned | 2020-05-28T10:03:28Z | |
| dc.date.available | 2020-05-28T10:03:28Z | |
| dc.date.issued | 2020 | eng |
| dc.description.abstract | 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. | eng |
| dc.description.version | published | de |
| dc.identifier.doi | 10.2312/mlvis.20201100 | eng |
| dc.identifier.ppn | 1700612867 | |
| dc.identifier.uri | https://kops.uni-konstanz.de/handle/123456789/49721 | |
| dc.language.iso | eng | eng |
| dc.rights | terms-of-use | |
| dc.rights.uri | https://rightsstatements.org/page/InC/1.0/ | |
| dc.subject.ddc | 004 | eng |
| dc.title | ModelSpeX : Model Specification Using Explainable Artificial Intelligence Methods | eng |
| dc.type | INPROCEEDINGS | de |
| dspace.entity.type | Publication | |
| kops.citation.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.}
} | |
| kops.citation.iso690 | 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 | deu |
| kops.citation.iso690 | 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, May 25, 2020 - May 29, 2020. In: ARCHAMBAULT, Daniel, ed. and others. Machine Learning Methods in Visualisation for Big Data 2020. Genf: The Eurographics Association, 2020, pp. 7-11. ISBN 978-3-03868-113-7. Available under: doi: 10.2312/mlvis.20201100 | 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/123456789/49721">
<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> | |
| kops.conferencefield | International Workshop on Machine Learning in Visualisation for Big Data : MLVis 2020, 25. Mai 2020 - 29. Mai 2020, Norrköping, Sweden | deu |
| kops.date.conferenceEnd | 2020-05-29 | eng |
| kops.date.conferenceStart | 2020-05-25 | eng |
| kops.description.funding | {"first":"dfg","second":"422037984"} | |
| kops.description.funding | {"first":"eu","second":"830892"} | |
| kops.description.openAccess | openaccessgreen | |
| kops.flag.knbibliography | true | |
| kops.identifier.nbn | urn:nbn:de:bsz:352-2-qm5kpmaxjly15 | |
| kops.location.conference | Norrköping, Sweden | eng |
| kops.sourcefield | ARCHAMBAULT, Daniel, Hrsg. und andere. <i>Machine Learning Methods in Visualisation for Big Data 2020</i>. Genf: The Eurographics Association, 2020, S. 7-11. ISBN 978-3-03868-113-7. Verfügbar unter: doi: 10.2312/mlvis.20201100 | deu |
| kops.sourcefield.plain | 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 | deu |
| kops.sourcefield.plain | ARCHAMBAULT, Daniel, ed. and others. Machine Learning Methods in Visualisation for Big Data 2020. Genf: The Eurographics Association, 2020, pp. 7-11. ISBN 978-3-03868-113-7. Available under: doi: 10.2312/mlvis.20201100 | eng |
| kops.title.conference | International Workshop on Machine Learning in Visualisation for Big Data : MLVis 2020 | eng |
| relation.isAuthorOfPublication | 7eeba0fc-d5f7-4e18-a226-9a1cd4c3fe11 | |
| relation.isAuthorOfPublication | ea6fe673-8015-4f18-88ad-f2312e0f27f6 | |
| relation.isAuthorOfPublication | da7dafb0-6003-4fd4-803c-11e1e72d621a | |
| relation.isAuthorOfPublication.latestForDiscovery | 7eeba0fc-d5f7-4e18-a226-9a1cd4c3fe11 | |
| source.bibliographicInfo.fromPage | 7 | eng |
| source.bibliographicInfo.toPage | 11 | eng |
| source.contributor.editor | Archambault, Daniel | |
| source.flag.etalEditor | true | eng |
| source.identifier.isbn | 978-3-03868-113-7 | eng |
| source.publisher | The Eurographics Association | eng |
| source.publisher.location | Genf | eng |
| source.title | Machine Learning Methods in Visualisation for Big Data 2020 | eng |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- Schlegel_2-qm5kpmaxjly15.pdf
- Größe:
- 287.22 KB
- Format:
- Adobe Portable Document Format
- Beschreibung:
