1. Repositório Aberto da Universidade do Porto
  2. FEUP - Faculdade de Engenharia
  3. FEUP - Dissertação
Please use this identifier to cite or link to this item: https://hdl.handle.net/10216/88482
Full metadata record
DC FieldValueLanguage
dc.creatorJohn Michael Salgado Cebola
dc.date.accessioned2019-02-02T22:32:07Z-
dc.date.available2019-02-02T22:32:07Z-
dc.date.issued2016-07-19
dc.date.submitted2016-07-29
dc.identifier.othersigarra:170137
dc.identifier.urihttps://repositorio-aberto.up.pt/handle/10216/88482-
dc.descriptionComparative study between the performance of Convolutional Networks using pretrained models and statistical generative models on tasks of image classification in semi-supervised enviroments.Study of multiple ensembles using these techniques and generated data from estimated pdfs.Pretrained Convents, LDA, pLSA, Fisher Vectors, Sparse-coded SPMs, TSVMs being the key models worked upon.
dc.language.isopor
dc.rightsopenAccess
dc.subjectEngenharia electrotécnica, electrónica e informática
dc.subjectElectrical engineering, Electronic engineering, Information engineering
dc.titlePre-trained Convolutional Networks and generative statiscial models: a study in semi-supervised learning
dc.typeDissertação
dc.contributor.uportoFaculdade de Engenharia
dc.identifier.tid201309084
dc.subject.fosCiências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática
dc.subject.fosEngineering and technology::Electrical engineering, Electronic engineering, Information engineering
thesis.degree.disciplineMestrado Integrado em Engenharia Electrotécnica e de Computadores
thesis.degree.grantorFaculdade de Engenharia
thesis.degree.grantorUniversidade do Porto
thesis.degree.level1
Appears in Collections:FEUP - Dissertação

Files in This Item:
File Description SizeFormat 
170137.pdfPre-trained Convolutional Networks and generative statiscial models: a study in semi-supervised learning6.22 MBAdobe PDFThumbnail
View/Open
Show simple item record Recommend this item Display Statistics


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.