Deep Dive into Deep Neural Networks with Flows - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Deep Dive into Deep Neural Networks with Flows

Résumé

Deep neural networks are becoming omnipresent in reason of their growing popularity in media and their daily use. However, their global complexity makes them hard to understand which emphasizes their black-box aspect and the lack of confidence given by their potential users. The use of tailored visual and interactive representations is one way to improve their explainability and trustworthy. Inspired by parallel coordinates and Sankey diagrams, this paper proposes a novel visual representation allowing tracing the progressive classification of a trained classification neural network by examining how each evaluation data is being processed by each network's layer. It is thus possible to observe which data classes are quickly recognized, unstable, or lately recognized. Such information provides insights to the user about the model architecture's pertinence and can guide on its improvement. The method has been validated on two classification neural networks inspired from the literature (LeNet5 and VGG16) using two public databases (MNIST and FashionMNIST).
Fichier principal
Vignette du fichier
Deep Dive into Deep Neural Networks with Flows (final).pdf (5.87 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02492393 , version 1 (26-02-2020)

Identifiants

  • HAL Id : hal-02492393 , version 1

Citer

Adrien Halnaut, Romain Giot, Romain Bourqui, David Auber. Deep Dive into Deep Neural Networks with Flows. Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020): IVAPP, Feb 2020, Valletta, Malta. pp.231-239. ⟨hal-02492393⟩
393 Consultations
115 Téléchargements

Partager

Gmail Facebook X LinkedIn More