Lecture 1: Supervised Machine Learning
Outline
Statistical Learning Theory (M1 ENS Ulm / ENS Paris-Saclay)
Lecture 2: Regression
Linear Regression and Logistic regression: particular cases of empirical risk regression
TP1: Linear Regression
Practical session 1: linear regression
Lecture 3: $k$-nearest neighbors
kNN: k-nearest neighbors
Lecture 6: PAC-Learning
Probably Approximately Correct
Lecture 4: Convex analysis/optimization
Convex functions
Exercises: Convex optimization
Practical session 3: linear regression
TP2: $k$-nearest neighbors
Practical session 2: kNN
Lecture 5: Convex analysis/optimization
Convex optimization
Exercises 5: Learning theory and PAC bounds
Practical session 5: Learning theory and PAC bounds
Lecture 7: Maximum likelihood
Maximum likelihood
Exercises 6: Learning theory and PAC bounds
Practical session 5: Learning theory and PAC bounds
TP6b: Régression linéaire & logistique, Analyse discriminante linéaire & quadratique
Practical session 4: Convex optimization
TP4: Convex optimization
Practical session 4: Convex optimization
Lecture 8: Reinforcement learning, Online Learning
Online learning
Lecture 9: Apprentissage non supervisé
Introduction
Practical session 10: LASSO Regression
Practical session 10: LASSO Regression
Lecture 10: Summary
Summary of the class
TD 12: Révisions
Practical session 12: Summary
TP 11: PCA et $K$-Means
Practical session 11: PCA and K-Means