Publikation:

Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations

Lade...
Vorschaubild

Dateien

Schlegel_2-9gt38k1euxha3.pdf
Schlegel_2-9gt38k1euxha3.pdfGröße: 1.58 MBDownloads: 57

Datum

2023

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

ArXiv-ID

Internationale Patentnummer

Angaben zur Forschungsförderung

Institutionen der Bundesrepublik Deutschland: 13N16242

Projekt

Open Access-Veröffentlichung
Open Access Bookpart
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published

Erschienen in

ARCHAMBAULT, Daniel, Hrsg., Ian NABNEY, Hrsg., Jaakko PELTONEN, Hrsg.. Machine Learning Methods in Visualisation for Big Data. Eindhoven: The Eurographics Association, 2023. ISBN 978-3-03868-224-0. Verfügbar unter: doi: 10.2312/mlvis.20231113

Zusammenfassung

The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models develops significantly, offering numerous techniques to extract explanations from models. However, evaluating explanations is often not trivial, and differences in applied metrics can be subtle, especially with non-intelligible data. Thus, there is a need for visualizations tailored to explore explanations for domains with such data, e.g., time series. We propose DAVOTS, an interactive visual analytics approach to explore raw time series data, activations of neural networks, and attributions in a dense-pixel visualization to gain insights into the data, models' decisions, and explanations. To further support users in exploring large datasets, we apply clustering approaches to the visualized data domains to highlight groups and present ordering strategies for individual and combined data exploration to facilitate finding patterns. We visualize a CNN trained on the FordA dataset to demonstrate the approach.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Konferenz

Machine Learning Methods in Visualisation for Big Data 2023 (MLVis 2023), 12. Juni 2023, Leipzig
Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690SCHLEGEL, Udo, Daniel A. KEIM, 2023. Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations. Machine Learning Methods in Visualisation for Big Data 2023 (MLVis 2023). Leipzig, 12. Juni 2023. In: ARCHAMBAULT, Daniel, Hrsg., Ian NABNEY, Hrsg., Jaakko PELTONEN, Hrsg.. Machine Learning Methods in Visualisation for Big Data. Eindhoven: The Eurographics Association, 2023. ISBN 978-3-03868-224-0. Verfügbar unter: doi: 10.2312/mlvis.20231113
BibTex
@inproceedings{Schlegel2023Inter-67522,
  year={2023},
  doi={10.2312/mlvis.20231113},
  title={Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations},
  isbn={978-3-03868-224-0},
  publisher={The Eurographics Association},
  address={Eindhoven},
  booktitle={Machine Learning Methods in Visualisation for Big Data},
  editor={Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko},
  author={Schlegel, Udo 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/123456789/67522">
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/67522/1/Schlegel_2-9gt38k1euxha3.pdf"/>
    <dcterms:abstract>The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models develops significantly, offering numerous techniques to extract explanations from models. However, evaluating explanations is often not trivial, and differences in applied metrics can be subtle, especially with non-intelligible data. Thus, there is a need for visualizations tailored to explore explanations for domains with such data, e.g., time series. We propose DAVOTS, an interactive visual analytics approach to explore raw time series data, activations of neural networks, and attributions in a dense-pixel visualization to gain insights into the data, models' decisions, and explanations. To further support users in exploring large datasets, we apply clustering approaches to the visualized data domains to highlight groups and present ordering strategies for individual and combined data exploration to facilitate finding patterns. We visualize a CNN trained on the FordA dataset to demonstrate the approach.</dcterms:abstract>
    <dc:contributor>Schlegel, Udo</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-08-07T15:11:59Z</dcterms:available>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:language>eng</dc:language>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/67522/1/Schlegel_2-9gt38k1euxha3.pdf"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2023</dcterms:issued>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/67522"/>
    <dc:creator>Schlegel, Udo</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-08-07T15:11:59Z</dc:date>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:title>Interactive Dense Pixel Visualizations for Time Series and Model Attribution Explanations</dcterms:title>
  </rdf:Description>
</rdf:RDF>

Interner Vermerk

xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter

Kontakt
URL der Originalveröffentl.

Prüfdatum der URL

Prüfungsdatum der Dissertation

Finanzierungsart

Kommentar zur Publikation

Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen