Please use this identifier to cite or link to this item: https://hdl.handle.net/10316/84362
DC FieldValueLanguage
dc.contributor.advisorRibeiro, Bernardete Martins-
dc.contributor.advisorMachado, Fernando Jorge Penousal Martins-
dc.contributor.authorSereno, David Martins Duarte-
dc.date.accessioned2019-01-24T23:11:09Z-
dc.date.available2019-01-24T23:11:09Z-
dc.date.issued2018-01-31-
dc.date.submitted2019-01-24-
dc.identifier.urihttps://hdl.handle.net/10316/84362-
dc.descriptionDissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia-
dc.description.abstractIn this work we have created a versatile evolutionary algorithm that can evolve an auto encoder neural network structure in an attempt to maximize the performance of different classifiers by using the resulting compressed version of the instances. During this process the algorithm searches for structures that compress as much as possible the representation to facilitate the classifiers training while maintain the necessary information in the datasets.This approach is set around the evolution of the number and size of the layers of a deep autoencoder, which is then trained using back propagation in a semi supervised fashion. The tests executed spanned multiple classifiers, and show promising results in which we observed an overall improvement in the classification on most the cases and, as expected, significant decrease in the training times.On the context of this thesis, a methodical approach was taken to analyze the impact that an autoencoder has, and how it behaves when its structure is evolved by means of Evolutionary Computation. As a stepping stone for the final work, preliminary experiments were performed, where multiple auto encoders were implemented and tested to confirm their correct behaviour and performance. To complement this a an evolutionary algorithm was tested in order to assess the usefulness and potential of evolving the structures, without imposing any restrictions on their shape.11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111eng
dc.description.abstractNo decorrer desta dissertação foi criado um algoritmo evolucionário altamente versátil capaz de evoluir com sucesso a estrutura de um rede neural de auto encoder, que procura maximizar a performance de diferentes classificadores. Durante este processo, o algoritmo procura maximizar a compressão de forma a facilitar a tarefa de treino dos classificadores sem que exista perda de performance dos mesmos.Esta abordagem consiste na evolução do número de camadas e número de neurónios presentes em cada uma, sendo a estrutura treinada de forma semi supervisionada através de retropropagação. Foram executados testes sobre um leque variado de classificadores, onde observámos uma melhoria na sua performance bem como uma significativa redução nos tempos de treino.No contexto desta tese , consta tambem uma análise metódica sobre o funcionamento e performance de autoencoders profundos e quais são as vantagens práticas de evoluir a sua estrutura. Como primeiro passo, no decorrer do trabalho, foram testados múltiplos autoencoders e abordagens evolucionárias de forma a confirmar o seu comportamento e performance.11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111 11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111 11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111 11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111 11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111por
dc.language.isoeng-
dc.rightsopenAccess-
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/-
dc.subjectDeep Learningpor
dc.subjectAutoEncoderpor
dc.subjectComputação Evolucionáriapor
dc.subjectDeep Learningeng
dc.subjectAutoEncodereng
dc.subjectEvolutionary Algorithmeng
dc.titleAutomatic Evolution of Deep AutoEncoderseng
dc.title.alternativeAutomatic Evolution of Deep AutoEncoderspor
dc.typemasterThesis-
degois.publication.locationDEI-FCTUC-
degois.publication.titleAutomatic Evolution of Deep AutoEncoderseng
dc.peerreviewedyes-
dc.identifier.tid202129594-
thesis.degree.disciplineInformática-
thesis.degree.grantorUniversidade de Coimbra-
thesis.degree.level1-
thesis.degree.nameMestrado em Engenharia Informática-
uc.degree.grantorUnitFaculdade de Ciências e Tecnologia - Departamento de Engenharia Informática-
uc.degree.grantorID0500-
uc.contributor.authorSereno, David Martins Duarte::0000-0001-7502-390X-
uc.degree.classification15-
uc.degree.presidentejuriCosta, Ernesto Jorge Fernandes-
uc.degree.elementojuriMachado, Fernando Jorge Penousal Martins-
uc.degree.elementojuriAraújo, Filipe João Boavida Mendonça Machado de-
uc.contributor.advisorRibeiro, Bernardete Martins::0000-0002-9770-7672-
uc.contributor.advisorMachado, Fernando Jorge Penousal Martins-
uc.controloAutoridadeSim-
item.grantfulltextopen-
item.fulltextCom Texto completo-
item.openairetypemasterThesis-
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
crisitem.advisor.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.advisor.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.advisor.parentresearchunitFaculty of Sciences and Technology-
crisitem.advisor.parentresearchunitFaculty of Sciences and Technology-
crisitem.advisor.orcid0000-0002-9770-7672-
crisitem.advisor.orcid0000-0002-6308-6484-
Appears in Collections:UC - Dissertações de Mestrado
Files in This Item:
File Description SizeFormat
Tese_INFOR.pdf1.4 MBAdobe PDFView/Open
Show simple item record

Page view(s) 50

584
checked on Apr 23, 2024

Download(s) 50

505
checked on Apr 23, 2024

Google ScholarTM

Check


This item is licensed under a Creative Commons License Creative Commons