Visualizing Learning Space in Neural Network Hidden Layers

Gabriel D. Cantareira, Fernando V. Paulovich, Elham Etemad

2020

Abstract

Analyzing and understanding how abstract representations of data are formed inside deep neural networks is a complex task. Among the different methods that have been developed to tackle this problem, multidimensional projection techniques have attained positive results in displaying the relationships between data instances, network layers or class features. However, these techniques are often static and lack a way to properly keep a stable space between observations and properly convey flow in such space. In this paper, we employ different dimensionality reduction techniques to create a visual space where the flow of information inside hidden layers can come to light. We discuss the application of each used tool and provide experiments that show how they can be combined to highlight new information about neural network optimization processes.

Download


Paper Citation


in Harvard Style

Cantareira G., Paulovich F. and Etemad E. (2020). Visualizing Learning Space in Neural Network Hidden Layers. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 3: IVAPP; ISBN 978-989-758-402-2, SciTePress, pages 110-121. DOI: 10.5220/0009168901100121


in Bibtex Style

@conference{ivapp20,
author={Gabriel D. Cantareira and Fernando V. Paulovich and Elham Etemad},
title={Visualizing Learning Space in Neural Network Hidden Layers},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 3: IVAPP},
year={2020},
pages={110-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009168901100121},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 3: IVAPP
TI - Visualizing Learning Space in Neural Network Hidden Layers
SN - 978-989-758-402-2
AU - Cantareira G.
AU - Paulovich F.
AU - Etemad E.
PY - 2020
SP - 110
EP - 121
DO - 10.5220/0009168901100121
PB - SciTePress