Please use this identifier to cite or link to this item:
https://hdl.handle.net/10216/88482
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.creator | John Michael Salgado Cebola | |
dc.date.accessioned | 2019-02-02T22:32:07Z | - |
dc.date.available | 2019-02-02T22:32:07Z | - |
dc.date.issued | 2016-07-19 | |
dc.date.submitted | 2016-07-29 | |
dc.identifier.other | sigarra:170137 | |
dc.identifier.uri | https://repositorio-aberto.up.pt/handle/10216/88482 | - |
dc.description | Comparative 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.iso | por | |
dc.rights | openAccess | |
dc.subject | Engenharia electrotécnica, electrónica e informática | |
dc.subject | Electrical engineering, Electronic engineering, Information engineering | |
dc.title | Pre-trained Convolutional Networks and generative statiscial models: a study in semi-supervised learning | |
dc.type | Dissertação | |
dc.contributor.uporto | Faculdade de Engenharia | |
dc.identifier.tid | 201309084 | |
dc.subject.fos | Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática | |
dc.subject.fos | Engineering and technology::Electrical engineering, Electronic engineering, Information engineering | |
thesis.degree.discipline | Mestrado Integrado em Engenharia Electrotécnica e de Computadores | |
thesis.degree.grantor | Faculdade de Engenharia | |
thesis.degree.grantor | Universidade do Porto | |
thesis.degree.level | 1 | |
Appears in Collections: | FEUP - Dissertação |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
170137.pdf | Pre-trained Convolutional Networks and generative statiscial models: a study in semi-supervised learning | 6.22 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.