Semi-automatic CNN Architectural Pruning using the Bayesian Case Model and Dimensionality Reduction Visualization

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorMarcilio-Jr, Wilson E.-
Autor(es): dc.creatorEler, Danilo-
Autor(es): dc.creatorGuilherme, Ivan-
Autor(es): dc.creatorHurter, C.-
Autor(es): dc.creatorPurchase, H.-
Autor(es): dc.creatorBouatouch, K.-
Data de aceite: dc.date.accessioned2025-08-21T19:44:39Z-
Data de disponibilização: dc.date.available2025-08-21T19:44:39Z-
Data de envio: dc.date.issued2022-11-29-
Data de envio: dc.date.issued2022-11-29-
Data de envio: dc.date.issued2021-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.5220/0010991000003124-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/237700-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/237700-
Descrição: dc.descriptionVisualization techniques have been applied to reasoning about complex machine learning models. These visual approaches aim to enhance the understanding of black-box models' decisions or guide in hyperparameters configuration, such as the number of layers and neurons/filters in deep neural networks. While several works address the architectural tuning of convolutional neural networks (CNNs), only a few works face the problem from a semi-automatic perspective. This work presents a novel application of the Bayesian Case Model that uses visualization strategies to convey the most important filters of convolutional layers for image classification. A heatmap coordinated with a scatterplot visualization emphasizes the filters with the most contribution to the CNN prediction. Our methodology is evaluated on a case study using the MNIST dataset.-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionSao Paulo State Univ UNESP, Dept Math & Comp Sci, Presidente Prudente, SP, Brazil-
Descrição: dc.descriptionSao Paulo State Univ UNESP, Dept Stat Appl Math & Comp, Rio Claro, SP, Brazil-
Descrição: dc.descriptionSao Paulo State Univ UNESP, Dept Math & Comp Sci, Presidente Prudente, SP, Brazil-
Descrição: dc.descriptionSao Paulo State Univ UNESP, Dept Stat Appl Math & Comp, Rio Claro, SP, Brazil-
Descrição: dc.descriptionFAPESP: 2018/17881-3-
Descrição: dc.descriptionFAPESP: 2018/25755-8-
Formato: dc.format203-209-
Idioma: dc.languageen-
Publicador: dc.publisherScitepress-
Relação: dc.relationProceedings Of The 17th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications (ivapp), Vol 3-
???dc.source???: dc.sourceWeb of Science-
Palavras-chave: dc.subjectCNN Pruning-
Palavras-chave: dc.subjectCase-based Reasoning-
Palavras-chave: dc.subjectVisualization-
Título: dc.titleSemi-automatic CNN Architectural Pruning using the Bayesian Case Model and Dimensionality Reduction Visualization-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.