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

Wilson E. Marcílio-Jr., Danilo M. Eler, Ivan R. Guilherme

2022

Abstract

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.

Paper Citation

in Harvard Style

E. Marcílio-Jr. W., Eler D. and Guilherme I. (2022). Semi-automatic CNN Architectural Pruning using the Bayesian Case Model and Dimensionality Reduction Visualization. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 3: IVAPP; ISBN 978-989-758-555-5, SciTePress, pages 203-209. DOI: 10.5220/0010991000003124

in Bibtex Style

@conference{ivapp22,
author={Wilson E. Marcílio-Jr. and Danilo M. Eler and Ivan R. Guilherme},
title={Semi-automatic CNN Architectural Pruning using the Bayesian Case Model and Dimensionality Reduction Visualization},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 3: IVAPP},
year={2022},
pages={203-209},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010991000003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 3: IVAPP
TI - Semi-automatic CNN Architectural Pruning using the Bayesian Case Model and Dimensionality Reduction Visualization
SN - 978-989-758-555-5
AU - E. Marcílio-Jr. W.
AU - Eler D.
AU - Guilherme I.
PY - 2022
SP - 203
EP - 209
DO - 10.5220/0010991000003124
PB - SciTePress