Compact visualization of DNN classification performances for interpretation and improvement - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2023

Compact visualization of DNN classification performances for interpretation and improvement

Résumé

In the research field of automatic classification tasks, deep neural networks (or DNN) are frequently used for their efficiency and adaptive nature. State-of-the-art architectures and pre-trained networks exist and can be converted and fine tuned to handle other classification tasks. However, because of their training phase requiring many computations and adjustments on the many parameters of the models, they suffer from a black-box effect that
Fichier principal
Vignette du fichier
Explainable_Deep_Learning__Methods_and_applications_chap3 (1).pdf (779.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04145832 , version 1 (30-06-2023)

Identifiants

Citer

Adrien Halnaut, Romain Giot, Romain Bourqui, David Auber. Compact visualization of DNN classification performances for interpretation and improvement. Explainable Deep Learning AI, Elsevier, pp.35-54, 2023, ⟨10.1016/B978-0-32-396098-4.00009-0⟩. ⟨hal-04145832⟩

Collections

CNRS
12 Consultations
24 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More