Logo CNRS Logo Université Paris Diderot
Logo tutelle Logo tutelle


Sur ce site

Sur le Web du CNRS

Accueil du site > Seminars > Séminaires théorie > Theory Club Thursday February 20 2020 at 13:30 in room 646A. Alexis Dubreuil: "Mechanics of neural computation".

Theory Club Thursday February 20 2020 at 13:30 in room 646A. Alexis Dubreuil: "Mechanics of neural computation"

Unless otherwise stated, seminars and defences take place at 11:30 in room 454A of Condorcet building.

Mechanics of neural computation

Alexis Dubreuil

Abstract: Describing how neural networks perform computations requires to understand how a macroscopic dynamics can emerge from a specific network structure. Statistical physics approaches to neural networks are particularly well suited to provide such a description. I will start by introducing the Hopfield model for associative memory, which has been extensively studied in the 80’s from a statistical physics point of view, and then show how this type of approach allows to address modern questions in neural computation. But as these standard approaches rely on the ability of modelers to propose neural structures implementing the desired computations, they quickly become difficult to deploy as one considers increasingly complex computations. I will present an approach, that combines machine learning algorithms and neural network theory, that I developed together with Srdjan Ostojic, to leverage this problem. This will be the occasion to further illustrate how the macroscopic dynamics of well defined order parameters relates to computation. Finally if time allows I will show how the notion of macroscopic dynamics can be used to describe computations performed by biological neural networks in behaving animals.

Thursday February 20 at 13:30 in room 646A

Contact : Équipe séminaires / Seminar team - Published on / Publié le 16 February 2020

In the same section :