This course is an advanced course focusing on the intersection of Statistics and Machine Learning. The goal is to study modern statistical methods for supervised and unsupervised learning, and the underlying theory for those methods. Numerous illustrations in the context of signal / image processing will be provided, through programming lab sessions in Python language.

- 1. Reminders on ML and Bayesian theory [Slides][Video]
- 2. Linear regression/classification approaches [Slides] [Slides (lab)] [Lab] [Notebook][Notebook (solved)] [Dataset] [Video]
- 3. Hierarchical clustering [Slides] [Slides (lab)] [Notebook] [Data1] [Data2] [Video]
- 4. Stochastic approximation algorithms [Slides] [Slides (lab)] [Lab] [Notebook] [Data] [Video]
- 5. Nonnegative matrix factorization [Slides] [Notebook] [Video]
- 6. Mixture models fitting and model order selection [Slides][Notebook][Data]
- 7. Inference on graphical models [Slides] [Notebook]
- Article for the exam [Link 1] [Link 2]
- Exam of past years [Subject] [Subject]
- Instructions for lab: Lab instructor: l'Emir Omar Chehab (PhD student, Inria Saclay)

Lab notebooks must be sent to: l-emir-omar.chehab@inria.fr.

- Emilie Chouzenoux -

Retour à la page précédente