On Diversity in Discriminative Neural Networks - Equipe Algorithm Architecture Interactions
Communication Dans Un Congrès Année : 2024

On Diversity in Discriminative Neural Networks

Résumé

Diversity is a concept of prime importance in almost all disciplines based on information processing. In telecommunications, for example, spatial, temporal, and frequency diversity, as well as redundant coding, are fundamental concepts that have enabled the design of extremely efficient systems. In machine learning, in particular with neural networks, diversity is not always a concept that is emphasized or at least clearly identified. This paper proposes a neural network architecture that builds upon various diversity principles, some of them already known, others more original. Our architecture obtains remarkable results, with a record self-supervised learning accuracy of 99. 57% in MNIST, and a top tier promising semi-supervised learning accuracy of 94.21% in CIFAR-10 using only 25 labels per class.
Fichier principal
Vignette du fichier
ISIVC_2024.pdf (282 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04661488 , version 1 (24-07-2024)

Identifiants

Citer

Brahim Oubaha, Claude Berrou, Xueyao Ji, Yehya Nasser, Raphaël Le Bidan. On Diversity in Discriminative Neural Networks. ISIVC 2024: IEEE 12th International Symposium on Signal, Image, Video and Communications, May 2024, Marrakech, Morocco. pp.1-6, ⟨10.1109/ISIVC61350.2024.10577798⟩. ⟨hal-04661488⟩
49 Consultations
34 Téléchargements

Altmetric

Partager

More