Publikation: Toward Out-of-Distribution Generalization Through Inductive Biases
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Sammlungen
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
State-of-the-art Machine Learning systems are able to process and analyze a large amount of data but they still struggle to generalize to out-of-distribution scenarios. To use Judea Pearl’s words, “Data are profoundly dumb" (Pearl&Mackenzie, 2018); possessing a model of the world, a representation through which to frame reality is a necessary requirement in order to discriminate between relevant and irrelevant information and to deal with unknown scenarios. The aim of this paper is to address the crucial challenge of out-of-distribution generalization in automated systems by developing an understanding of how human agents build models to act in a dynamic environment. The steps needed to reach this goal are described by Pearl through the metaphor of the Ladder of Causation. In this paper, I support the relevance of inductive biases in order for an agent to reach the second rung on the Ladder: that of actively interacting with the environment.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
MORUZZI, Caterina, 2022. Toward Out-of-Distribution Generalization Through Inductive Biases. Philosophy and Theory of Artificial Intelligence 2021 : PTAI 2021. Gothenburg, Sweden, 27. Sept. 2021 - 28. Sept. 2021. In: MÜLLER, Vincent C., ed.. Philosophy and Theory of Artificial Intelligence 2021. Cham: Springer, 2022, pp. 57-66. Studies in Applied Philosophy, Epistemology and Rational Ethics. 63. ISBN 978-3-031-09152-0. Available under: doi: 10.1007/978-3-031-09153-7_5BibTex
@inproceedings{Moruzzi2022Towar-57918, year={2022}, doi={10.1007/978-3-031-09153-7_5}, title={Toward Out-of-Distribution Generalization Through Inductive Biases}, number={63}, isbn={978-3-031-09152-0}, publisher={Springer}, address={Cham}, series={Studies in Applied Philosophy, Epistemology and Rational Ethics}, booktitle={Philosophy and Theory of Artificial Intelligence 2021}, pages={57--66}, editor={Müller, Vincent C.}, author={Moruzzi, Caterina} }
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/123456789/57918"> <dcterms:issued>2022</dcterms:issued> <dc:rights>terms-of-use</dc:rights> <dc:language>eng</dc:language> <dcterms:title>Toward Out-of-Distribution Generalization Through Inductive Biases</dcterms:title> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-07-04T07:01:55Z</dc:date> <dc:creator>Moruzzi, Caterina</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-07-04T07:01:55Z</dcterms:available> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/40"/> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:contributor>Moruzzi, Caterina</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/40"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57918"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:abstract xml:lang="eng">State-of-the-art Machine Learning systems are able to process and analyze a large amount of data but they still struggle to generalize to out-of-distribution scenarios. To use Judea Pearl’s words, “Data are profoundly dumb" (Pearl&Mackenzie, 2018); possessing a model of the world, a representation through which to frame reality is a necessary requirement in order to discriminate between relevant and irrelevant information and to deal with unknown scenarios. The aim of this paper is to address the crucial challenge of out-of-distribution generalization in automated systems by developing an understanding of how human agents build models to act in a dynamic environment. The steps needed to reach this goal are described by Pearl through the metaphor of the Ladder of Causation. In this paper, I support the relevance of inductive biases in order for an agent to reach the second rung on the Ladder: that of actively interacting with the environment.</dcterms:abstract> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> </rdf:Description> </rdf:RDF>