Invariance and Stability of Deep Convolutional Representations

Abstract : In this paper, we study deep signal representations that are near-invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information. This is achieved by generalizing the multilayer kernel introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable, and that models from this functional space, such as a large class of convolutional neural networks, may enjoy the same stability.
Type de document :
Communication dans un congrès
NIPS 2017 - 31st Conference on Advances in Neural Information Processing Systems , Dec 2017, Los Angeles, CA, United States
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01630265
Contributeur : Alberto Bietti <>
Soumis le : mardi 7 novembre 2017 - 13:53:07
Dernière modification le : mardi 14 novembre 2017 - 15:56:12

Identifiants

  • HAL Id : hal-01630265, version 1

Collections

Citation

Alberto Bietti, Julien Mairal. Invariance and Stability of Deep Convolutional Representations. NIPS 2017 - 31st Conference on Advances in Neural Information Processing Systems , Dec 2017, Los Angeles, CA, United States. 〈hal-01630265〉

Partager

Métriques

Consultations de la notice

95

Téléchargements de fichiers

102