Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks

Detalhes bibliográficos
Autor(a) principal: Martins, Guilherme de Oliveira Crespo
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/127958
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics
id RCAP_59eec78a12d619c730b6b9fa162fd397
oai_identifier_str oai:run.unl.pt:10362/127958
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural NetworksMachine learningDeep neural networksParticles warmo ptimizationGradient descentComputer visionDissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced AnalyticsDeep Neural Networks attempt to simulate the behaviour of the brain to solve complex problems.Today, they are currently used for various real world application ssuch as natural language processing, image recognition, self-driving cars,and much more. However, these models, can be very computationally expensive and take a considerable amount of time to train. In this thesis, we attempt to use swarm intelligence to optimize Deep Neural Networks with a smaller computational budget. To achieve this goal, we implement a method that takes any model and selects the layer that can contribute the most for the optimization of said model. Afterwards, we further optimize the layer selected with the Particle Swarm Optimization algorithm in an attempt to take advantage of its ability to surpass local optimums.Castelli, MauroBakurov, IllyaRUNMartins, Guilherme de Oliveira Crespo2021-11-19T12:00:18Z2021-11-092021-11-09T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/127958TID:202792617enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:07:43Zoai:run.unl.pt:10362/127958Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:46:14.363669Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
title Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
spellingShingle Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
Martins, Guilherme de Oliveira Crespo
Machine learning
Deep neural networks
Particles warmo ptimization
Gradient descent
Computer vision
title_short Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
title_full Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
title_fullStr Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
title_full_unstemmed Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
title_sort Single layer optimization with Particle Swarm Optimization: A new approach to optimize Deep Neural Networks
author Martins, Guilherme de Oliveira Crespo
author_facet Martins, Guilherme de Oliveira Crespo
author_role author
dc.contributor.none.fl_str_mv Castelli, Mauro
Bakurov, Illya
RUN
dc.contributor.author.fl_str_mv Martins, Guilherme de Oliveira Crespo
dc.subject.por.fl_str_mv Machine learning
Deep neural networks
Particles warmo ptimization
Gradient descent
Computer vision
topic Machine learning
Deep neural networks
Particles warmo ptimization
Gradient descent
Computer vision
description Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics
publishDate 2021
dc.date.none.fl_str_mv 2021-11-19T12:00:18Z
2021-11-09
2021-11-09T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/127958
TID:202792617
url http://hdl.handle.net/10362/127958
identifier_str_mv TID:202792617
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138066292539392

Registros relacionados