Invariance and Stability of Deep Convolutional Representations - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2017

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.
Fichier principal
Vignette du fichier
stability-nips.pdf (372.04 Ko) Télécharger le fichier
Loading...

Dates and versions

hal-01630265 , version 1 (07-11-2017)

Identifiers

  • HAL Id : hal-01630265 , version 1

Cite

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. pp.1622-1632. ⟨hal-01630265⟩
764 View
731 Download

Share

More