GAN Hyperparameters search through Genetic Algorithm
| Autor(a) principal: | |
|---|---|
| Data de Publicação: | 2022 |
| Tipo de documento: | Dissertação |
| Idioma: | eng |
| Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
| Texto Completo: | http://hdl.handle.net/10362/135552 |
Resumo: | Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science |
| id |
RCAP_a733e9663a434009c4fe026556dfcde5 |
|---|---|
| oai_identifier_str |
oai:run.unl.pt:10362/135552 |
| network_acronym_str |
RCAP |
| network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
| repository_id_str |
7160 |
| spelling |
GAN Hyperparameters search through Genetic AlgorithmArtificial neural networksGenerative Adversarial NetworksDissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data ScienceRecent developments in Deep Learning are remarkable when it comes to generative models. The main reason for such progress is because of Generative Adversarial Networks (GANs) [1]. Introduced in a paper by Ian Goodfellow in 2014 GANs are machine learning models that are made of two neural networks: a Generator and a Discriminator. These two compete amongst each other to generate new, synthetic instances of data that resemble the real one. Despite their great potential, there are present challenges in their training, which include training instability, mode collapse, and vanishing gradient. A lot of research has been done on how to overcome these challenges, however, there was no significant proof found on whether modern techniques consistently outperform vanilla GAN. The performances of GANs are also highly dependent on the dataset they are trained on. One of the main challenges is related to the search for hyperparameters. In this thesis, we try to overcome this challenge by applying an evolutionary algorithm to search for the best hyperparameters for a WGAN. We use Kullback-Leibler divergence to calculate the fitness of the individuals, and in the end, we select the best set of parameters generated by the evolutionary algorithm. The parameters of the best-selected individuals are maintained throughout the generations. We compare our approach with the standard hyperparameters given by the state-of-art.Castelli, MauroRUNTammaro, Umberto2022-03-30T17:11:03Z2022-03-072022-03-07T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/135552TID:202979792enginfo: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:RCAAP2024-03-11T05:13:55Zoai:run.unl.pt:10362/135552Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:48:27.023693Repositório 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 |
GAN Hyperparameters search through Genetic Algorithm |
| title |
GAN Hyperparameters search through Genetic Algorithm |
| spellingShingle |
GAN Hyperparameters search through Genetic Algorithm Tammaro, Umberto Artificial neural networks Generative Adversarial Networks |
| title_short |
GAN Hyperparameters search through Genetic Algorithm |
| title_full |
GAN Hyperparameters search through Genetic Algorithm |
| title_fullStr |
GAN Hyperparameters search through Genetic Algorithm |
| title_full_unstemmed |
GAN Hyperparameters search through Genetic Algorithm |
| title_sort |
GAN Hyperparameters search through Genetic Algorithm |
| author |
Tammaro, Umberto |
| author_facet |
Tammaro, Umberto |
| author_role |
author |
| dc.contributor.none.fl_str_mv |
Castelli, Mauro RUN |
| dc.contributor.author.fl_str_mv |
Tammaro, Umberto |
| dc.subject.por.fl_str_mv |
Artificial neural networks Generative Adversarial Networks |
| topic |
Artificial neural networks Generative Adversarial Networks |
| description |
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science |
| publishDate |
2022 |
| dc.date.none.fl_str_mv |
2022-03-30T17:11:03Z 2022-03-07 2022-03-07T00:00:00Z |
| 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/10362/135552 TID:202979792 |
| url |
http://hdl.handle.net/10362/135552 |
| identifier_str_mv |
TID:202979792 |
| 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_ |
1799138085548589056 |