Accueil/ expose
The brain as an optimal efficient adaptive learner
mardi 16 mai 2017

Loading the player...

Conférence de Sophie Deneve lors du colloquium Data Science Colloquium  de l'ENS.

Understanding how the brain learns to compute functions reliably, efficiently, and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could presumably be learned by adjusting connection weights in a recurrent biological neural network. However, this is greatly complicated by the credit assignment problem for learning in recurrent networks, e.g., the contribution of each connection to the global output error cannot be determined based only on locally accessible quantities to the synapse. Combining tools from adaptive control theory and efficient coding theories, we propose that neural circuits can indeed learn complex dynamic tasks with local synaptic plasticity rules as long as they associate two experimentally established neural mechanisms. First, they should receive top-down feedbacks driving both their activity and their synaptic plasticity. Second, inhibitory interneurons should maintain a tight balance between excitation and inhibition in the circuit. The resulting networks could learn arbitrary dynamical systems and produce irregular spike trains as variable as those observed experimentally. Yet, this variability in single neurons may hide an extremely efficient and robust computation at the population level.


Voir aussi

  • Du bruit dans le cerveau ?
    Sophie Deneve
  • Can Big Data cure Cancer?
    Jean-Philippe Vert
  • What physics can tell us about inferenc...
    Cristopher Moore
  • Beyond stochastic gradient descent for l...
    Francis Bach
  • Cosmostatistics: Tackling Big Data from ...
    Jean-Luc Starck
  • Searching for interaction networks in pr...
    Rémi Monasson
  • Brain-computer interfaces: two concurren...
    Maureen Clerc
  • Machine learning in scientific workflow...
    Balàzs Kégl
  • Learning Graph Inverse Problems with Neu...
    Joan Bruna
  • Towards developmental AI
    Emmanuel Dupoux
  • Optimization's Hidden Gift to Learning: ...
    Nathan Srebro
  • Prototype-based classifiers and relevanc...
    Michael Biehl
  • Generative modelling with diffusion : th...
    Valentin De Bortoli
Sophie Deneve
Ecole normale supérieure

Plus sur cet auteur
Voir la fiche de l'auteur

Institutions : Ecole normale supérieure-PSL

Cursus :

Sophie Deneveest chercheur CNRS dans l'équipe "Group for Neural Theory" au Laboratoire de Neurosciences Cognitives, Département d'études cognitives à l'Ecole normale supérieure.

Cliquer ICI pour fermer
Téléchargements :
   - Télécharger la vidéo
   - Télécharger l'audio (mp3)

Dernière mise à jour : 04/07/2017