Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
10.605 Lectures/texts in conference proceedings
You are here:
View Item 
  •   DSpace Home
  • Congressos
  • Severo Ochoa Research Seminars at BSC
  • 2nd Severo Ochoa Research Seminar Lectures at BSC, Barcelona, 2015-2016
  • View Item
  •   DSpace Home
  • Congressos
  • Severo Ochoa Research Seminars at BSC
  • 2nd Severo Ochoa Research Seminar Lectures at BSC, Barcelona, 2015-2016
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Talk 1: Convolutional neural networks against the curse of dimensionality

Thumbnail
View/Open
41-42 2015-16 SORS BoA TALK 1 Convolutional Neural.pdf (211,2Kb)
  View UPCommons Usage Statistics
  LA Referencia / Recolecta stats
Includes usage data since 2022
Cita com:
hdl:2117/96654

Show full item record
Bruna, Joan
Document typeConference report
Defense date2016-09-10
PublisherBarcelona Supercomputing Center
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 3.0 Spain
This work is protected by the corresponding intellectual and industrial property rights. Except where otherwise noted, its contents are licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
Convolutional Neural Networks are a powerful class of non-linear representations that have shown through numerous supervised learning tasks their ability to extract rich information from images, speech and text, with excellent statistical generalization. These are examples of truly high-dimensional signals, in which classical statistical models suffer from the curse of dimensionality, referring to their inability to generalize well unless provided with exponentially large amounts of training data. In this talk we will start by studying statistical models defined from wavelet scattering networks, a class of CNNs where the convolutional filter banks are given by complex, multi-resolution wavelet families. The reasons for such success lie on their ability to preserve discriminative information while being stable with respect to high-dimensional deformations, providing a framework that partially extends to trained CNNs. We will give conditions under which signals can be recovered from their scattering coefficients, and will discuss a family of Gibbs processes defined by CNN sufficient statistics, from which one can sample image and auditory textures. Although the scattering recovery is non-convex and corresponds to a generalized phase recovery problem, gradient descent algorithms show good empirical performance and enjoy weak convergence properties. We will discuss connections with non-linear compressed sensing, applications to texture synthesis, inverse problems such as super-resolution, as well as an application to sentence modeling, where convolutions are generalized using associative trees to generate robust sentence representations.
CitationBruna, Joan. Talk 1: Convolutional neural networks against the curse of dimensionality. A: 2nd Severo Ochoa Research Seminar Lectures at BSC, Barcelona, 2015-2016 : Deep Learning Seminar. "Book of abstracts". Barcelona: Barcelona Supercomputing Center, 2016, p. 40-42. 
URIhttp://hdl.handle.net/2117/96654
Collections
  • Severo Ochoa Research Seminars at BSC - 2nd Severo Ochoa Research Seminar Lectures at BSC, Barcelona, 2015-2016 [17]
  View UPCommons Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
41-42 2015-16 S ... 1 Convolutional Neural.pdf211,2KbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Metadata under:Metadata under CC0
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina