Machine Learning CS-433

This course is offered jointly by the TML and MLO groups. Previous year’s website: ML 2023.
See here for the ML4Science projects.

Contact us: Use the discussion forum. You can also email the head assistant Corentin Dumery, and CC both instructors.

Instructors: Nicolas Flammarion and Martin Jaggi

 
Teaching Assistants
  • Aditya Varre
  • Alexander Hägele
  • Atli Kosson
  • Corentin Dumery
  • Dongyang Fan
  • El Mahdi Chayti
  • Francesco D’Angelo
  • Gizem Yüce
  • Hristo Papazov
  • Karami Hojjat
  • Ke Wang
  • Oguz Yüksel
  • Robin Zbinden
  • Sevda Ogut
  • Simin Fan
 Student Assistants
  • Adam Ezzaim
  • Alexandre Mayer
  • Alexi Semiz
  • Antoine Bergerault
  • Arthur Wuhrmann
  • Berke Argin
  • Luka Radic
  • Marija Zelic
  • Mirco Bonfrisco
  • Nadezhda Ilieva
  • Said Gurbuz
  • Sara Zatezalo
  • Sebastien Chahoud
  • Yann Becker
  • Zihan Yu
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: 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: Thursday 16.01.2025 from 15h15 to 18h15, 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 counts 10% and is due Nov 1st.
    • Project 2 counts 30% and is due Dec 19th.
  • 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
10/9 Introduction, Linear Regression 01a,01b
01c,01d		    
11/9 Loss functions   Lab 1  
17/9 Optimization 02a    
18/9 Optimization   Lab 2 Project 1 start
24/9 Least Squares, Overfitting 03    
25/9 Max Likelihood, Ridge Regression, Lasso   Lab 3  
1/10 Generalization, Model Selection, and Validation 04    
2/10 Bias-Variance decomposition   Lab 4  
8/10 Classification 05    
9/10 Logistic Regression   Lab 5  
15/10 Support Vector Machines 06a,06b    
16/10 K-Nearest Neighbor   Lab 6  
29/10 Kernel Regression 07    
30/10 Neural Networks – Basics, Representation Power   Lab 7

Proj. 1 due 1.11.
05/11 Neural Networks – Backpropagation, Activation Functions 08   Project 2 start
06/11 Neural Networks – CNNs, Regularization, Data Augmentation, Dropout   Lab 8  
12/11 Neural Networks – Transformers 09    
13/11 Adversarial ML   Lab 9  
19/11 Ethics and Fairness in ML 10    
20/11 Unsupervised Learning, K-Means, Gaussian Mixture Models   Lab 10  
26/11 Gaussian Mixture Models, EM algorithm      
27/11 Matrix Factorizations   Lab 11 & Project Q&A  
03/12 Text Representation Learning      
04/12 Self-supervised learning, LLMs   Lab 12  
10/12 LLMs      
11/12 GANs + Diffusion models   Lab 13  
17/12 Guest lecture, T.B.D.      
18/12 Projects pitch session (optional)     Proj. 2 due 19.12.

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, UniL or other academic institution, or one of the predefined ML challenges.

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