Seminar

Past

Deep residual networks and differential equations

MAD-Stat. Seminar

Gérard Biau

  • Date21 November 2024
  • Time 11h00 - 12h15
  • Room Auditorium 3

Résumé

Deep learning has become a prominent approach for many applications, such as computer vision or neural language processing. However, the mathematical understanding of these methods is still incomplete. A recent approach is to consider neural networks as discretized versions of differential equations. I will first give an overview of this emerging field and then discuss new results on residual neural networks, which are state-of-the-art deep learning models.

Other seminars

To be announced

  • Seminar

  • MAD-Stat. Seminar

  • Date 4 March 2027

  • Place Auditorium JJ Laffont

  • Speaker or organiser Agnes Lagnoux (Ecole Normale Supérieure - Université Paris Sciences & Lettres)

Détails

Convergence Rates for Distribution Matching with Sliced Optimal Transport

  • Seminar

  • MAD-Stat. Seminar

  • Date 10 December 2026

  • Place Auditorium 6

  • Speaker or organiser Gauthier Louis Thurin (Université de Bordeaux)

Détails

Limits of uniform spanning trees and forests

  • Seminar

  • MAD-Stat. Seminar

  • Date 3 December 2026

  • Place Auditorium JJ Laffont

  • Speaker or organiser Eleanor Archer (Université Paris-Dauphine)

Détails