Introduction to statistical learning
N. VAYATIS
LearningMachine Learning

Prè-requis

Undergraduate courses in Analysis and Probability

Objectif du cours

The course presents the mathematical foundations for supervised learning.

Organisation des séances

  • 8 theoretical sessions
  • 3 practical sessions

Mode de validation

  • Part 1 : partial exam (mandatory)
  • Part 2 : final exam or paper review project (report+oral presentation)
  • Re-take : written exam or project (proposed only for students who attended Part 1 and Part 2)

Références

  • S. Boucheron, O. Bousquet, and G. Lugosi. Theory of Classification: a Survey of Recent Advances. ESAIM: Probability and Statistics, 9:323375, 2005.
  • L. Devroye, L. Györfi, G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer, New York, 1996.

http://nvayatis.perso.math.cnrs.fr/ISLcourse-2017.html

Thèmes abordés

  • Typology of learning problems
  • Statistical models and main algorithms for classification, scoring, …
  •  Performance criteria and inference principles
  •  Convex risk minimization
  •  Complexity measures
  •  Aggregation and ensemble methods
  •  Main theorems
Les intervenants

Nicolas Vayatis

(CMLA, ENS Cachan)

voir les autres cours du 1er semestre