Institut de Mathématiques de Marseille, UMR 7373




Rechercher


Accueil > Équipes de recherche > Signal et Image (SI) > Manifestations scientifiques

Manifestations scientifiques (colloques, écoles,...)

par Lozingot Eric - publié le , mis à jour le

Agenda

Séminaire

groupe de travail

Manifestation scientifique

  • Du 19 au 23 novembre - WORKSHOP AND DOCTORAL SCHOOL

    iTWIST : international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques

    Résumé : WORKSHOP AND DOCTORAL SCHOOL,
    4th edition.
    -
    The advent of increased computing capabilities, along with recent theoretical and numerical breakthroughs in the fields of signal processing, computational harmonic analysis, inverse problem solving, high-dimensional statistics and convex optimization, have boosted interactions between low-complexity data models (e.g., sparse or low-rank data models) and novel data sensing techniques.
    In a nutshell, low-complexity data models aim at capturing, modeling and exploiting “just the information you need” in the ubiquitous data deluge characterizing any scientific or technological achievements. High dimensional objects can be thus reconstructed using little information. However, further developments and novel ideas are still required to meet new challenges, especially for efficiently dealing with complex data structures of "real life" applications and for interconnecting such models with other theoretical and applied fields.
    ​The iTWIST workshop aims at fostering collaboration between international scientific teams for developing new theories, applications and generalizations of low-complexity models. This is why this event emphasizes dissemination of ideas through both specific oral/poster presentations and free discussions.
    For this edition, ITWIST will be divided into two parts, a 2-day doctoral school, followed by the actual workshop for three days.
    -
    Sujets :
    - Application of low-complexity models in non-convex/non-linear inverse problems such as phase retrieval, blind deconvolution, blind calibration, or dictionary learning.
    - Machine learning, deep learning, compressive statistical learning and generalized high-dimensional inference of low-complexity statistical models.
    - Optimization methods for recovering low-complexity data representations (e.g., low-rank or tensor decomposition).
    - Information theory, high-dimensional (convex) geometry and randomness.
    - Novel definition of low-complexity models (discrete-valued signals, co-sparsity, mixed/group norm, model-based, tensor/manifold models).
    - Sensing and processing of low-complexity signals on manifolds and graphs.
    - Complexity and accuracy tradeoffs in numerical methods/optimization.
    - Simulation and/or developments of novel electronic/optical compressive sensors.
    -
    Organizing Committee :
    Sandrine Anthoine (Aix-Marseille Université, France), General Chair
    Yannick Boursier (CPPM, France)
    Laurent Jacques (UCLouvain, Belgium)
    Christine De Mol (Université Libre de Bruxelles, Belgium)
    -
    Partenaires :
    - Aix-Marseille Université (FIR colloques AMU)
    - Centre International de Rencontres Mathématiques (CIRM)
    - Centre National de la Recherche Scientifique (CNRS)
    - ED184
    - FNRS
    - GDR MIA
    - GDR MOA
    - IN2P3
    - Institut de Mathématiques de Marseille (I2M)
    - LabEx Archimède
    - LabEx CARMIN
    -

    Site web du workshop
    JPEG - 28.3 ko

    Autre lien : CIRM

    Lieu : CIRM - 163 avenue de Luminy
    Case 916
    13288 MARSEILLE - Cedex 9
    France

    Exporter cet événement

  • Vendredi 30 novembre 09:45-16:30 - JOURNÉE

    Journée Mathématiques du Deep Learning

    Résumé : JOURNÉE,
    dans le cadre du Séminaire Signal et Apprentissage
    -
    L’objectif de la journée est double : une partie tutorielle fera le point sur les avancées mathématiques du deep learning ; une autre partie sera l’occasion de faire le point sur ce qui se fait en deep learning pour le traitement du signal et l’image.
    -
    Programme :
    - 9h45 Accueil
    - 10h00-12h00 Thierry Artières (LIS, Marseille) : Etat des lieux en Deep Learning
    - 12h00-13h30 Pause / Repas
    - 13h30-14h30 Jakob Verbeek (Thoth, INRIA Grenoble) : Recent results on deep learning for shape matching, machine translation, and generative image modeling
    - 14h30-15h00 Pause
    - 15h00-16h30 François Malgouyres (IMT, Toulouse) : Multilinear compressive sensing and an application to convolutional linear networks
    -
    Organisateurs :
    - Sandrine Anthoine (I2M, Marseille)
    - Caroline Chaux (I2M, Marseille)
    - Hachem Kadri (LIS, Marseille)
    - Clothilde Mélot (I2M, Marseille)
    - Bruno Torrésani (I2M, Marseille)
    -

    Site web de la Journée
    JPEG - 57.2 ko

    Autre lien : FRUMAM

    Lieu : FRUMAM - Salle des séminaires 2ème étage - Aix-Marseille Université - Site St Charles
    3, place Victor Hugo - case 39
    13331 MARSEILLE Cedex 03

    Exporter cet événement

Agenda des manifestations scientifiques organisées ou co-organisées par l’équipe SI.

Types de manifestations concernées : colloques (international conferences), congrès, symposiums, mois ou semestres thématiques, écoles, ateliers (workshops), rencontres scientifiques, journées,...

Voir en ligne : Toutes les manifestations scientifiques de l’I2M