Learning sparse structures for physics-inspired compressed sensing - ENSTA Bretagne - École nationale supérieure de techniques avancées Bretagne Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Learning sparse structures for physics-inspired compressed sensing

Clément Dorffer
Gilles Le Chenadec
Angélique Drémeau


In underwater acoustics, shallow water environments act as modal dispersive waveguides when considering lowfrequency sources. In this context, propagating signals can be described as a sum of few modal components, each of them propagating according to its own wavenumber. Estimating these wavenumbers is of key interest to understand the propagating environment as well as the emitting source. To solve this problem, we proposed recently a Bayesian approach exploiting a sparsity-inforcing prior. When dealing with broadband sources, this model can be further improved by integrating the particular dependence linking the wavenumbers from one frequency to the other. In this contribution, we propose to resort to a new approach relying on a restricted Boltzmann machine, exploited as a generic structured sparsity-inforcing model. This model, derived from deep Bayesian networks, can indeed be efficiently learned on physically realistic simulated data using well-known and proven algorithms.
Fichier principal
Vignette du fichier
ITWIST_2020.pdf (209.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03461818 , version 1 (01-12-2021)


  • HAL Id : hal-03461818 , version 1


Clément Dorffer, Thomas Paviet-Salomon, Gilles Le Chenadec, Angélique Drémeau. Learning sparse structures for physics-inspired compressed sensing. itwist 2020, Dec 2020, Virtual Nantes, France. ⟨hal-03461818⟩
12 Consultations
9 Téléchargements


Gmail Facebook X LinkedIn More