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

Autor(es)

Marcilio-Jr, Wilson E. ; Eler, Danilo ; Guilherme, Ivan ; Hurter, C ; Purchase, H ; Bouatouch, K

• Tipo de documento: Artigo Científico
• Fonte: PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 4; v. N/A, p. 7-pg., 2022-01-01.

Resumo

Visualization 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. (AU)

• Processo FAPESP: 18/25755-8 - Representação visual multinível para auxiliar a exploração de conjuntos de dados
• Beneficiário: Wilson Estécio Marcílio Júnior
• Modalidade de apoio: Bolsas no Brasil - Programa Capacitação - Treinamento Técnico
• Processo FAPESP: 18/17881-3 - Representação visual multinível para auxiliar a exploração de conjuntos de dados
• Beneficiário: Danilo Medeiros Eler
• Modalidade de apoio: Auxílio à Pesquisa - Regular