M2 course, ENS Lyon: Machine Learning

Machine Learning

Lecturer

Aurélien Garivier

Course description

The aim of this course is to introduce the main problems and theoretical aspects of Machine Learning.
The focus will be mainly on supervised classification, with a few extensions on non-supervised learning (clustering) and regression.
Each course will be the opportunity of a focus on a particular technique or tool of general interest (such as deviation inequalities, statistical tests, stochastic optimization, etc.).

The aspects of Machine Learning relative to reinforcement learning will not be addressed in this course: they are at the core of the course CR01: Optimal Decision Making and Online Optimization. Online learning will also be studied during the first Winter School.

Course outline

Prerequisite

Basic knowledge of probability theory, linear algebra and analysis over the reals

Evaluation

In addition to homework and in-class exercices, students will chose betwenn

  • a research article to analyze
  • a participation in the Défi IA 2019, you can watch the videos of presentation. Warning: the competition stops on 01.13 at 9pm. After that, no submission will be possible. Only the last submission wiil be taken into account in the final ranking.

In both case, they will prepare a written report and an oral presentation. The final grade will be a function of all these.

Maybe useful information

Bibliography

  1. Understanding Machine Learning, From Theory to Algorithms, by Shai Shalev-Shwartz and Shai Ben-David
  2. A Probabilistic Theory of Pattern Recognition, by Luc Devroye, Laslzlo Gyorfi and Gabor Lugosi
  3. The Elements of Statistical Learning, by Trevor Hastie, Robert Tibshirani and Jerome Friedman
  4. Introduction to Nonparametric Estimation, by Alexander Tsybakov
  5. Lectures notes on advanced Statistical Learning , by Martin Wainwright

Notebooks

  1. Introduction to ML: synthetic example
  2. Presentation of the MNIST dataset and nearest-neighbor classification