• français
    • English
    français
  • Login
Help
View Item 
  •   Home
  • Dynamique des Fluides (DynFluid)
  • View Item
  • Home
  • Dynamique des Fluides (DynFluid)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Deep Recurrent Encoder: an end-to-end network to model magnetoencephalography at scale

Article dans une revue avec comité de lecture
Author
CHEHAB, Omar
419361 Université Paris-Saclay
DEFOSSEZ, Alexandre
267305 Facebook AI Research [Paris] [FAIR]
GRAMFORT, Alexandre
118511 Inria Saclay - Ile de France
419361 Université Paris-Saclay
KING, Jean-Remi
267305 Facebook AI Research [Paris] [FAIR]
59704 École normale supérieure - Paris [ENS-PSL]
ccLOISEAU, Jean-Christophe
134975 Laboratoire de Dynamique des Fluides [DynFluid]

URI
http://hdl.handle.net/10985/23068
DOI
10.51628/001c.38668
Date
2022-10
Journal
Neurons, Behavior, Data analysis, and Theory

Abstract

Understanding how the brain responds to sensory inputs from non-invasive brain recordings like magnetoencephalography (MEG) can be particularly challenging: (i) the high-dimensional dynamics of mass neuronal activity are notoriously difficult to model, (ii) signals can greatly vary across subjects and trials and (iii) the relationship between these brain responses and the stimulus features is non-trivial. These challenges have led the community to develop a variety of preprocessing and analytical (almost exclusively linear) methods, each designed to tackle one of these issues. Instead, we propose to address these challenges through a specific end-to-end deep learning architecture, trained to predict the MEG responses of multiple subjects at once. We successfully test this approach on a large cohort of MEG recordings acquired during a one-hour reading task. Our Deep Recurrent Encoder (DRE) reliably predicts MEG responses to words with a three-fold improvement over classic linear methods. We further describe a simple variable importance analysis to investigate the MEG representations learnt by our model and recover the expected evoked responses to word length and word frequency. Last, we show that, contrary to linear encoders, our model captures modulations of the brain response in relation to baseline fluctuations in the alpha frequency band. The quantitative improvement of the present deep learning approach paves the way to a better characterization of the complex dynamics of brain activity from large MEG datasets.

Files in this item

Name:
DYNFLUID_NBDT_2022_LOISEAU.pdf
Size:
8.809Mb
Format:
PDF
Description:
Deep Recurrent Encoder: an ...
Embargoed until:
2023-05-12
View/Open
CC BY
This document is available under CC BY license

Collections

  • Dynamique des Fluides (DynFluid)

Related items

Showing items related by title, author, creator and subject.

  • Global Stability Analyses Unraveling Roughness-induced Transition Mechanisms 
    Article dans une revue avec comité de lecture
    LOISEAU, Jean-Christophe; ROBINET, Jean-Christophe; CHERUBINI, Stefania; LERICHE, Emmanuel (Elsevier, 2015)
    The linear global instability and resulting transition to turbulence induced by a cylindrical roughness element of heighth and diameter d=3h immersed within an incompressible boundary layer flow along a flat plate is ...
  • Influence of the Shape on the Roughness-Induced Transition 
    Ouvrage scientifique
    LOISEAU, Jean-Christophe; CHERUBINI, Stefania; ROBINET, Jean-Christophe; LERICHE, Emmanuel (Springer, 2015)
    lobal instability analysis of the three-dimensional flow past two rough- ness elements of different shape, namely a cylinder and a bump, is presented. In both cases, the eigenspectrum is made of modes characterised by a ...
  • Bifurcation analysis and frequency prediction in shear-driven cavity flow 
    Article dans une revue avec comité de lecture
    BENGANA, Y.; LOISEAU, Jean-Christophe; ROBINET, Jean-Christophe; TUCKERMAN, L. S. (Cambridge University Press (CUP), 2019)
    A comprehensive study of the two-dimensional incompressible shear-driven flow in an open square cavity is carried out. Two successive bifurcations lead to two limit cycles with different frequencies and different numbers ...
  • Numerical investigation of the interaction between laminar to turbulent transition and the wake of an airfoil 
    Article dans une revue avec comité de lecture
    DUCOIN, A.; LOISEAU, Jean-Christophe; ROBINET, Jean-Christophe (Elsevier, 2016)
    The objective of this work is to investigate numerically the different physical mechanisms of the transition to turbulence of a separated boundary-layer flow over an airfoil at low angle of attack. In this study, the ...
  • Time-Stepping and Krylov Method for large scale instability problems 
    Chapitre d'ouvrage scientifique
    LOISEAU, Jean-Christophe; BUCCI, Michele Alessandro; CHERUBINI, Stefania; ROBINET, Jean-Christophe (Springer, 2018)
    With the ever increasing computational power available and the development of high-performances computing, investigating the properties of realistic very large-scale nonlinear dynamical systems has become reachable. It ...

Browse

All SAMCommunities & CollectionsAuthorsIssue DateCenter / InstitutionThis CollectionAuthorsIssue DateCenter / Institution

Newsletter

Latest newsletterPrevious newsletters

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales