Samples Classification Analysis Across DNN Layers with Fractal Curves - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Samples Classification Analysis Across DNN Layers with Fractal Curves

Résumé

Deep Neural Networks are becoming the prominent solution when using machine learning models. However, they suffer from a blackbox effect that renders complicated their inner workings interpretation and thus the understanding of their successes and failures. Information visualization is one way among others to help in their interpretability and hypothesis deduction. This paper presents a novel way to visualize a trained DNN to depict at the same time its architecture and its way of treating the classes of a test dataset at the layer level. In this way, it is possible to visually detect where the DNN starts to be able to discriminate the classes or where it could decrease its separation ability (and thus detect an oversized network). We have implemented the approach and validated it using several well-known datasets and networks. Results show the approach is promising and deserves further studies.
Fichier principal
Vignette du fichier
lncs126630047.pdf (774.17 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03111634 , version 1 (15-01-2021)

Identifiants

  • HAL Id : hal-03111634 , version 1

Citer

Adrien Halnaut, Romain Giot, Romain Bourqui, D. Auber. Samples Classification Analysis Across DNN Layers with Fractal Curves. ICPR 2020's Workshop Explainable Deep Learning for AI, Jan 2021, Milano (virtual), Italy. ⟨hal-03111634⟩

Collections

CNRS
132 Consultations
164 Téléchargements

Partager

Gmail Facebook X LinkedIn More