Machine Learning CS-433

This course is offered jointly by the TML and MLO groups. Previous year’s website: ML 2025.
See here for the ML4Science projects.

Contact us: Use the discussion forum. You can also email the lead assistants Gizem Yuce and Simin Fan at [email protected], and CC both instructors.

Instructors: Nicolas Flammarion and Martin Jaggi

 
Teaching Assistants
  • Alejandro Hernandez Cano
  • Benedikt Edler von Querfuth
  • Fares Fawzi
  • Hantao Zhang
  • Johan Wenckstern
  • Kaustubh Ponkshe
  • Liangze Jiang
  • Mark Rofin
  • Mingqiao Ye
  • Vinko Sabolcec
 Student Assistants
  • Anna Lavrenko
  • Ananya Gupta
  • Benedek Balla
  • Giacomo Porpiglia
  • Miquel Lopez
  • Nahush Kohle
  • Naser Kazemi
  • Rali Lahlou
  • Semanur Avsar
  • Strahinja Nikolic
  • Tommaso Capone
  • Yinan Hu
Lectures Tuesday 16:15 – 18:00 in Rolex Learning Center
  Wednesday 10:15 – 12:00 in Rolex Learning Center
Exercises Thursday 14:15 – 16:00

Rooms: CO123, INF1, INF119, INJ218, INM202, INR219 
(assignment see course info sheet)
Language:   English
Credits :   8 ECTS

For a summary of the logistics of this course, see the course info sheet here (PDF).
(and also here is a link to official coursebook information).

Special Announcements

  • Exam Date: T.B.D. in the January exam session, in SwissTech.
  • The links for the exercises signup and the discussion forum. All other materials are here on this page and github.
  • Projects: There will be two group projects during the course.
    • Project 1 is not graded and is due Oct 29th.
    • Project 2 counts 30% and is due Dec 17th.
  • The videos of the lectures for each week will be available. Labs and projects will be in Python. See Lab 1 to get started.
  • Code Repository for Labs, Projects, Lecture notes: github.com/epfml/ML_course
  • the exam is closed book but you are allowed one crib sheet (A4 size paper, both sides can be used); bring a pen and white eraser; you find the exams from the past years with solutions here:

Detailed Schedule

Lecture notes from each class are made available on github here, and videos here on mediaspace.

Date Topics Covered Lectures Exercises Projects
8/9 Introduction, Linear Regression 01a,01b    
9/9 Loss functions 01c Lab 1  
15/9 Optimization 02a    
16/9 Optimization   Lab 2 Project 1 start
22/9 Least Squares, Overfitting      
23/9 Max Likelihood, Ridge Regression, Lasso   Lab 3  
29/9 Generalization, Model Selection, and Validation      
30/9 Bias-Variance decomposition   Lab 4  
6/10 Classification      
7/10 Logistic Regression   Lab 5  
13/10 Support Vector Machines      
14/10 K-Nearest Neighbor   Lab 6  
27/10 Kernel Regression      
28/10 Neural Networks – Basics, Representation Power   Lab 7

Proj. 1 due 29.10.
03/11 Neural Networks – Backpropagation, Activation Functions     Project 2 start
04/11 Neural Networks – CNNs, Regularization, Data Augmentation, Dropout   Lab 8  
10/11 Neural Networks – Transformers      
11/11 Adversarial ML   Lab 9  
17/11 Ethics and Fairness in ML      
18/11 Unsupervised Learning, K-Means, Gaussian Mixture Models   Lab 10  
24/11 Gaussian Mixture Models, EM algorithm      
25/11 Matrix Factorizations   Lab 11 & Project Q&A  
01/12 Text Representation Learning      
02/12 LLMs   Lab 12 & Project Q&A  
8/12 LLMs, Self-supervised Learning      
9/12 GANs + Diffusion models   Lab 13  
15/12 Guest lecture, Edouard Grave: “Audio/Speech LM”      
16/12 Projects pitch session (optional)     Proj. 2 due 17.12.

Textbooks

(not mandatory)

Gilbert Strang, Linear Algebra and Learning from Data
Christopher Bishop, Pattern Recognition and Machine Learning
Shai Shalev-Shwartz, Shai Ben-David, Understanding Machine Learning
Michael Nielsen, Neural Networks and Deep Learning

Projects & ML4Science

Projects are done either in ML4Science in collaboration with any lab of EPFL, or any other academic institution.

All info about the interdisciplinary ML4Science projects is available on the separate page here.