Rémi Flamary

Theory of statistical learning M1

Courses

• Introduction to machine learning and pattern recognition [PDF]
  • Introduction
  • Unsupervised learning
  • Supervised learning
  • Implementation
• Linear regression [PDF]
  • Least Squares
  • Ridge regression
  • Variable selection with the Lasso
• Linear classification [PDF]
  • Linear Discriminant Analysis
  • Logistic regression
  • Rosenblatt's perceptron
  • Support Vector Machines

Exercises

• Linear regression [PDF]
• Linear classification

Practical sessions

• Linear regression [PDF] [ECoG_Finger.npz]
• Linear classification [PDF][digits.npz]

Practical sessions will require a working Python environnement with te libraries Numpy/Scipy and Matplotlib installed. You can get such an environnement for Windows/Linux/MacOSX on Anaconda.

Here is a list of nice references for the Pythoon :

• Tutorial Numpy
• Doc Numpy
• Doc Scipy
• Doc ScMatplotlib/pylab

Project and competition

The final project is a Kaggle InClass competition Data Science UCA 2019 with real data. In order to participate to the competition, a Kaggle account is required. The competition is private and you will need the URL received by email to participate.

At the end of the competition, you will present as a group the data and the machine learning methods used in the competition. Then you will have a short presentation to explain what you did specifically during the competition. A report using IEEE double column format will also be part of the final grade.