Mostra el registre d'ítem simple

dc.contributor.authorGarcia Gasulla, Dario
dc.contributor.authorVilalta Arias, Armand
dc.contributor.authorParés Pont, Ferran
dc.contributor.authorMoreno Vázquez, Jonatan
dc.contributor.authorAyguadé Parra, Eduard
dc.contributor.authorLabarta Mancho, Jesús José
dc.contributor.authorCortés García, Claudio Ulises
dc.contributor.authorSuzumura, Toyotaro
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2020-07-09T09:20:47Z
dc.date.available2020-07-09T09:20:47Z
dc.date.issued2017
dc.identifier.citationGarcia-Gasulla, D. [et al.]. Building graph representations of deep vector embeddings. A: Workshop on Semantic Deep Learning. "Proceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2): September 19, 2017, Montpellier, France". Stroudsburg, PA: Association for Computational Linguistics, 2017, p. 9-15.
dc.identifier.otherhttps://arxiv.org/abs/1707.07465
dc.identifier.urihttp://hdl.handle.net/2117/192717
dc.description.abstractPatterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector embedding spaces, which enables the use of traditional machine learning algorithms on top of them. In this short paper we propose the construction of a graph embedding space instead, introducing a methodology to transform the knowledge coded within a deep convolutional network into a topological space (i.e. a network). We outline how such graph can hold data instances, data features, relations between instances and features, and relations among features. Finally, we introduce some preliminary experiments to illustrate how the resultant graph embedding space can be exploited through graph analytics algorithms
dc.description.sponsorshipThis work is partially supported by the Joint Study Agreement no. W156463 under the IBM/BSC Deep Learning Center agreement, by the Spanish Government through Programa Severo Ochoa (SEV-2015- 0493), by the Spanish Ministry of Science and Technology through TIN2015-65316-P project, by the Generalitat de Catalunya (contracts 2014-SGR-1051), and by the Core Research for Evolutional Science and Technology (CREST) program of Japan Science and Technology Agency (JST).
dc.format.extent7 p.
dc.language.isoeng
dc.publisherAssociation for Computational Linguistics
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshMachine learning
dc.subject.lcshImage analysis
dc.subject.lcshImage data mining
dc.subject.otherArtificial intelligence
dc.subject.otherDeep learning
dc.subject.otherEmbedding
dc.subject.otherComplex networks
dc.subject.otherGraph
dc.subject.otherCommunity detection
dc.subject.otherTransfer learning
dc.titleBuilding graph representations of deep vector embeddings
dc.typeConference lecture
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacImatges -- Anàlisi
dc.contributor.groupUniversitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic
dc.contributor.groupUniversitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.aclweb.org/anthology/W17-7302/
dc.rights.accessOpen Access
local.identifier.drac28845458
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/AGAUR/V PRI/2014 SGR 1051
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO//TIN2015-65316-P/ES/COMPUTACION DE ALTAS PRESTACIONES VII/
local.citation.authorGarcia-Gasulla, D.; Vilalta, A.; Parés, F.; Moreno, J.; Ayguadé, E.; Labarta, J.; Cortés, U.; Suzumura, T.
local.citation.contributorWorkshop on Semantic Deep Learning
local.citation.pubplaceStroudsburg, PA
local.citation.publicationNameProceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2): September 19, 2017, Montpellier, France
local.citation.startingPage9
local.citation.endingPage15


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple