En poursuivant votre navigation sur ce site, vous acceptez l'utilisation d'un simple cookie d'identification. Aucune autre exploitation n'est faite de ce cookie. OK
1

One signal processing view on deep learning - lecture 2

Bookmarks Report an error
Multi angle
Authors : Oyallon, Edouard (Author of the conference)
CIRM (Publisher )

Loading the player...

Abstract : Since 2012, deep neural networks have led to outstanding results in many various applications, literally exceeding any previously existing methods, in texts, images, sounds, videos, graphs... They consist of a cascade of parametrized linear and non-linear operators whose parameters are optimized to achieve a fixed task. This talk addresses 4 aspects of deep learning through the lens of signal processing. First, we explain image classification in the context of supervised learning. Then, we show several empirical results that allow us to get some insights about the black box of neural networks. Third, we explain how neural networks create invariant representation: in the specific case of translation, it is possible to design predefined neural networks which are stable to translation, namely the Scattering Transform. Finally, we discuss several recent statistical learning, about the generalization and approximation properties of this deep machinery.

Keywords : apprentissage profond; traitement du signal; transformée en scattering

MSC Codes :
94A12 - Signal theory (characterization, reconstruction, filtering, etc.)
68T07 - Artificial neural networks and deep learning

    Information on the Video

    Film maker : Hennenfent, Guillaume
    Language : English
    Available date : 22/02/2021
    Conference Date : 28/01/2021
    Subseries : Research School
    arXiv category : Machine Learning ; Computer Vision and Pattern Recognition
    Mathematical Area(s) : Computer Science
    Format : MP4 (.mp4) - HD
    Video Time : 01:24:01
    Targeted Audience : Researchers
    Download : https://videos.cirm-math.fr/2021-01-28_Oyallon_2.mp4

Information on the Event

Event Title : Mathematics, Signal Processing and Learning / Mathématiques, traitement du signal et apprentissage
Event Organizers : Anthoine, Sandrine ; Chaux, Caroline ; Mélot, Clothilde ; Richard, Frédéric
Dates : 25/01/2021 - 29/01/2021
Event Year : 2021
Event URL : https://conferences.cirm-math.fr/2472.html

Citation Data

DOI : 10.24350/CIRM.V.19705803
Cite this video as: Oyallon, Edouard (2021). One signal processing view on deep learning - lecture 2. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19705803
URI : http://dx.doi.org/10.24350/CIRM.V.19705803

See Also

Bibliography



Bookmarks Report an error