Publikation: Towards an Interpretable Latent Space : an Intuitive Comparison of Autoencoders with Variational Autoencoders
Lade...
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2018
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
Proceedings of the Workshop on Visualization for AI Explainability 2018 (VISxAI). 2018
Zusammenfassung
We present an intuitive comparison of Auto-Encoders (AE) with Variational Auto-Encoders (VAE) by visualizing their latent activations. In order to do this, we trained an AE and the corresponding VAE on the MNIST dataset. To give a feeling for the latent compression, we visualize the latent activations of the AE/VAE by displaying the 4 latent variables in a parallel coordinate system. We provide an introduction to the architectures of AEs/VAEs and draw a comparison between the two models.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
visualization, machine learning, explainable machine learning, autoencoders, variational autoencoders, latent space
Konferenz
IEEE VIS 2018, 21. Okt. 2018 - 26. Okt. 2018, Berlin
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
SPINNER, Thilo, Jonas KÖRNER, Jochen GÖRTLER, Oliver DEUSSEN, 2018. Towards an Interpretable Latent Space : an Intuitive Comparison of Autoencoders with Variational Autoencoders. IEEE VIS 2018. Berlin, 21. Okt. 2018 - 26. Okt. 2018. In: Proceedings of the Workshop on Visualization for AI Explainability 2018 (VISxAI). 2018BibTex
@inproceedings{Spinner2018Towar-43657, year={2018}, title={Towards an Interpretable Latent Space : an Intuitive Comparison of Autoencoders with Variational Autoencoders}, url={https://thilospinner.com/towards-an-interpretable-latent-space/}, booktitle={Proceedings of the Workshop on Visualization for AI Explainability 2018 (VISxAI)}, author={Spinner, Thilo and Körner, Jonas and Görtler, Jochen and Deussen, Oliver} }
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/123456789/43657"> <dc:creator>Spinner, Thilo</dc:creator> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-11-05T12:45:45Z</dc:date> <dc:creator>Görtler, Jochen</dc:creator> <dcterms:abstract xml:lang="eng">We present an intuitive comparison of Auto-Encoders (AE) with Variational Auto-Encoders (VAE) by visualizing their latent activations. In order to do this, we trained an AE and the corresponding VAE on the MNIST dataset. To give a feeling for the latent compression, we visualize the latent activations of the AE/VAE by displaying the 4 latent variables in a parallel coordinate system. We provide an introduction to the architectures of AEs/VAEs and draw a comparison between the two models.</dcterms:abstract> <dc:creator>Körner, Jonas</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:creator>Deussen, Oliver</dc:creator> <dc:contributor>Spinner, Thilo</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-11-05T12:45:45Z</dcterms:available> <dc:contributor>Deussen, Oliver</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/43657"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dcterms:title>Towards an Interpretable Latent Space : an Intuitive Comparison of Autoencoders with Variational Autoencoders</dcterms:title> <dc:contributor>Görtler, Jochen</dc:contributor> <dcterms:issued>2018</dcterms:issued> <dc:language>eng</dc:language> <dc:contributor>Körner, Jonas</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> </rdf:Description> </rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
URL der Originalveröffentl.
Prüfdatum der URL
2018-10-27
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja