David Picard IMAGINE/LIGM, École des Ponts ParisTech CNRS, Univ Gustave Eiffel 6-8, Av Blaise Pascal - Cité Descartes Champs-sur-Marne 77455 Marne-la-Vallée cedex 2 Home  /  Email  /  GitHub  /  Google Scholar  /  Resume

Teaching 2025

Introduction to machine learning (MALAP). 6 lectures + 4 lab sessions (with the goal of implementing actual algorithms).

• All slides in book format: pdf
• 1. Introduction, ERM, k-NN: html, ipynb
• 2. Linear models: html, ipynb
• 3. SVM and kernels: html, ipynb
• 4. Decision trees and ensembling: html, ipynb
• 5. Neural networks: html, ipynb
• 5. Time series: html, ipynb
• 7. Clustering and introduction to PAC: html, ipynb
• Lab 0. Numerical algebra: ipynb
• Lab 1. Nearest neighbor classifier: ipynb
• Lab 2. Support vector machines: ipynb
• Lab 3. Decision trees: ipynb
• Lab 4. Metric learning: ipynb

Generative Models for Visual Content at M2 Data Science - Intitut Polytechnique de Paris. Slides made with Manim, very heavy, not super practical in hindsight.

• 1. Diffusion models: html
• 2. Flow Matching: html
• 3. Controlability: html
• 4. Auto Regressive models: html
• 5. Video generation: html