Exposé & Table-ronde @ CAp21, 14 juin 2021

Expressivity, sparsity and identifiability in deep neural networks

https://cap2021.sciencesconf.org/resource/page/id/6

Sparse audio declipping: a paper and two open source toolboxes available

Our paper on “Sparsity-based audio declipping methods: selected overview, new algorithms, and large-scale evaluation” is accepted for publication in the IEEE/ACM Transactions on Audio, Speech and Language Processing.

Here are some audio examples.

The SPADE Toolbox used to reproduce these results is available under the  BSD-3-Clause License  (https://opensource.org/licenses/BSD-3-Clause).

We also publicly release the code of  A-SPADE (Analysis Sparse Audio DEclipper).

Estimation quotidienne de l’évolution du taux de reproduction de la COVID19 par optimisation convexe

L’optimisation convexe permet d’estimer quotidiennement l’évolution du taux de reproduction de la Covid-19, au cours du temps et à travers les départements.

Détails dans  l’actualité scientifique intitulée « Comment mieux estimer l’évolution du taux de reproduction de la Covid-19 ? » mise en ligne sur le site web de l’INP.

Thematic Month on “Mathematics for Signals, Images and Structured Data @ CIRM, early 2021

Dear colleagues

it is our pleasure to announce the upcoming one month program on Mathematics for Signals, Images and Structured Data

to be held at CIRM ( Marseille), January 25 -February 26, 2021. The program will consist in a research school on

• Mathematics, signal processing and learning (25 – 29 January 2021) and four conferences on

  • Harmonic analysis, multiscale representations and applications to large-scale data, modeling and numerical simulations (1 – 5 February 2021)
  • Statistical analysis of images and their derived objects (8 – 12 February 2021)
  • Mathematics for Audio and Music Signal Processing (15 – 19 February 2021)
  • (Bio-)medical imaging, neuro-imaging and related signals (22 – 26 February 2021) More information is available on the web site of the program, that will be updated on a regular basis : https://conferences.cirm-math.fr/2331.html If you are interested in receiving updates concerning the program (including updated schedule , call for participation, call for submission, opening of registration,…), please register on the dedicated mailing list cirm2021@listes.math.cnrs.fr, by clicking on “s’abonner”(left menu) on the web site https://listes.math.cnrs.fr/wws/info/cirm2021 We look forward to seeing you in 2021 ! The Signal-Image team at I2M (Institut de Mathématiques de Marseille). Thematic month on Mathematics for Signals, Images and Structured Data CIRM, February 2021 https://conferences.cirm-math.fr/2331.html

Download the annoucement in pdf format

Postdoc offer

The DANTE team at ENS de Lyon, France is seeking highly qualified candidates for a postdoctoral position on the algorithmic and mathematical foundations of resource-efficient machine learning, in the context of the ACADEMICS project (Machine Learning & Data Science for Complex and Dynamical Models) funded by the IDEXLyon.

Sample research topics include (download pdf version of the offer here): Expressivity and Robustness of Sparse Deep Networks; Provable Algorithms for Sparse Deep Learning; Random Sketches for Efficient Manifold & Graph-based Learning.

Starting date and duration: spring 2020, one year – renewable

Location : http://www.ens-lyon.fr/en/

Scientific Contact: Rémi Gribonval (firstname.lastname@inria.fr)

To apply: Applicants are requested to send a detailed CV, a list of publications and a brief statement of research interests. This material, together with two letters of reference, shall be sent to Rémi Gribonval


Talk @ 4TU Meeting on Mathematics of Deepl Learning, Delft, Nov 5

https://www.4tu.nl/ami/en/Agenda-Events/a4-4tu-poster-5-november-2019.pdf

Talk @ GDR ISIS Day “Théorie du deep learning”, Oct 17th 2019, CNAM Paris

link to the program of the day

Panel session @ GRETSI2019 on Signal Processing & AI

Plenary Talk @SampTA 2019, Bordeaux, July 8-12 2019

https://sampta2019.sciencesconf.org/

Talk @ Sparsity4PSL Summer School, Paris, June 27th

https://sparsity4psl.github.io/