Interpreting neural decoding models using grouped model reliance

Lade...
Vorschaubild
Dateien
Valentin_2-1b2p0oaw030ow3.pdf
Valentin_2-1b2p0oaw030ow3.pdfGröße: 3.97 MBDownloads: 205
Datum
2020
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Gold
Sammlungen
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
PLoS Computational Biology. Public Library of Science (PLoS). 2020, 16(1), e1007148. eISSN 1553-7358. Available under: doi: 10.1371/journal.pcbi.1007148
Zusammenfassung

Machine learning algorithms are becoming increasingly popular for decoding psychological constructs based on neural data. However, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches, there is a need for methods that allow to interpret trained decoding models. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0–9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. The present results confirm previous findings insofar as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and topography varied considerably between individuals, pointing to more pronounced inter-individual differences than previously reported.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
150 Psychologie
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690VALENTIN, Simon, Maximilian HARKOTTE, Tzvetan G. POPOV, 2020. Interpreting neural decoding models using grouped model reliance. In: PLoS Computational Biology. Public Library of Science (PLoS). 2020, 16(1), e1007148. eISSN 1553-7358. Available under: doi: 10.1371/journal.pcbi.1007148
BibTex
@article{Valentin2020-01Inter-49265,
  year={2020},
  doi={10.1371/journal.pcbi.1007148},
  title={Interpreting neural decoding models using grouped model reliance},
  number={1},
  volume={16},
  journal={PLoS Computational Biology},
  author={Valentin, Simon and Harkotte, Maximilian and Popov, Tzvetan G.},
  note={Article Number: e1007148}
}
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/123456789/49265">
    <dc:contributor>Harkotte, Maximilian</dc:contributor>
    <dcterms:abstract xml:lang="eng">Machine learning algorithms are becoming increasingly popular for decoding psychological constructs based on neural data. However, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches, there is a need for methods that allow to interpret trained decoding models. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0–9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. The present results confirm previous findings insofar as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and topography varied considerably between individuals, pointing to more pronounced inter-individual differences than previously reported.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-04-23T08:55:19Z</dcterms:available>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49265/1/Valentin_2-1b2p0oaw030ow3.pdf"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43"/>
    <dc:contributor>Popov, Tzvetan G.</dc:contributor>
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-04-23T08:55:19Z</dc:date>
    <dcterms:title>Interpreting neural decoding models using grouped model reliance</dcterms:title>
    <dc:language>eng</dc:language>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
    <dcterms:issued>2020-01</dcterms:issued>
    <dc:creator>Popov, Tzvetan G.</dc:creator>
    <dc:creator>Valentin, Simon</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43"/>
    <dc:creator>Harkotte, Maximilian</dc:creator>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Valentin, Simon</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/49265"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49265/1/Valentin_2-1b2p0oaw030ow3.pdf"/>
  </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
Nein
Begutachtet
Ja
Diese Publikation teilen