Show simple item record

dc.contributor.authorMazuelas S.en_US
dc.contributor.authorPerez A.en_US
dc.date.accessioned2020-10-06T19:29:39Z
dc.date.available2020-10-06T19:29:39Z
dc.date.issued2020-08-01
dc.identifier.issn978-1-64368-100-9
dc.identifier.issn978-1-64368-101-6
dc.identifier.urihttp://hdl.handle.net/20.500.11824/1155
dc.description.abstractDifferent types of training data have led to numerous schemes for supervised classification. Current learning techniques are tailored to one specific scheme and cannot handle general ensembles of training samples. This paper presents a unifying framework for supervised classification with general ensembles of training samples, and proposes the learning methodology of generalized robust risk minimization (GRRM). The paper shows how current and novel supervision schemes can be addressed under the proposed framework by representing the relationship between examples at prediction and training via probabilistic transformations. The results show that GRRM can handle different types of training samples in a unified manner, and enable new supervision schemes that aggregate general ensembles of training samples.en_US
dc.description.sponsorshipRYC-2016-19383en_US
dc.formatapplication/pdfen_US
dc.language.isoengen_US
dc.publisherProceedings of the 24th European Conference on Artificial Intelligence-ECAIen_US
dc.relationES/1PE/SEV-2017-0718en_US
dc.relationES/1PE/TIN2017-82626-Ren_US
dc.relationEUS/BERC/BERC.2018-2021en_US
dc.relationEUS/ELKARTEKen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/en_US
dc.subjectsupervised classificationen_US
dc.subjectweak supervisionen_US
dc.subjectdomain adaptationen_US
dc.subjectnoisy labelsen_US
dc.titleGeneral supervision via probabilistic transformationsen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.typeinfo:eu-repo/semantics/publishedVersionen_US
dc.relation.publisherversionhttp://ecai2020.eu/papers/494_paper.pdfen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/openAccess
Except where otherwise noted, this item's license is described as info:eu-repo/semantics/openAccess