DATAIA Seminars | «Can current neural networks provide a satisfactory model of the human brain?» - Stanislas Dehaene

01/13/2021 04:00 pm 01/13/2021 05:00 pm UTC DATAIA Seminars | «Can current neural networks provide a satisfactory model of the human brain?» - Stanislas Dehaene

Stanislas Dehaene (Collège de France) est l’animateur du séminaire DATAIA du mois de janvier qui porte sur le thème « Can current neural networks provide a satisfactory model of the human brain ? ».

Résumé :
I will argue that, in spite of their major recent successes, both in solving real-world problems and in predicting brain responses in human and non-human primates, most current neural networks are essentially limited. The human brain keeps the upper hand in its ability to (1) learn from a very small number of examples, sometimes a single trial, using Bayesian-style reasoning (“the child as a scientist”); (2) discover compact, abstract, explicit representations of knowledge, in a form which can be shared with others; (3) learn from others and learn with others; (4) learn compositional representations in a “language of thought”. I will describe extremely simple experiments in which the human brain acquires information in a single trial and represents its in a quasi-linguistic form, which is currently hard to capture with present-day neural networks.

Informations pratiques :
Le webinaire aura lieu le 13 janvier à 16h00 (CET) et il sera transmis en live broadcasting .

Il est recommandé d'utiliser Google Chrome , Firefox , ou l'App BlueJeans (https://www.bluejeans.com/downloads) pour se connecter.

S'inscrire au séminaire

chez soi
Thematic : Doctorate Education Innovation Research

Dans le cadre de son animation scientifique, l'Institut DATAIA Paris-Saclay organise des séminaires mensuels visant à échanger autour de l'IA.

  • Public
    Réservé à certains publics
  • Event type
    Conférence / séminaire
  • Conditions

    Inscription gratuite mais obligatoire

  • Dates
    Wednesday 13 January, 16:00
    04:00 pm - 05:00 pm
  • Location
    chez soi

Stanislas Dehaene (Collège de France) est l’animateur du séminaire DATAIA du mois de janvier qui porte sur le thème « Can current neural networks provide a satisfactory model of the human brain ? ».

Résumé :
I will argue that, in spite of their major recent successes, both in solving real-world problems and in predicting brain responses in human and non-human primates, most current neural networks are essentially limited. The human brain keeps the upper hand in its ability to (1) learn from a very small number of examples, sometimes a single trial, using Bayesian-style reasoning (“the child as a scientist”); (2) discover compact, abstract, explicit representations of knowledge, in a form which can be shared with others; (3) learn from others and learn with others; (4) learn compositional representations in a “language of thought”. I will describe extremely simple experiments in which the human brain acquires information in a single trial and represents its in a quasi-linguistic form, which is currently hard to capture with present-day neural networks.

Informations pratiques :
Le webinaire aura lieu le 13 janvier à 16h00 (CET) et il sera transmis en live broadcasting .

Il est recommandé d'utiliser Google Chrome , Firefox , ou l'App BlueJeans (https://www.bluejeans.com/downloads) pour se connecter.

S'inscrire au séminaire