Machine Learning CS-433

This course is offered jointly by the TML and MLO groups. Previous year’s website: ML 2019.
See here for all information about the ML4Science projects.

Contact us: Use the discussion forum, or some of the contact details below:

Instructor Nicolas Flammarion Instructor Martin Jaggi
Office INJ 336 Office INJ 341
Email [email protected] Email [email protected]
Office Hours By appointment Office Hours By appointment
Teaching Assistants
  • Maksym Andriushchenko
  • Arnout Devos
  • Semih Günel
  • Prakhar Gupta
  • Mahdi Hajibabaei
  • Sai Praneeth Karimireddy
  • Anastasiia Koloskova
  • Tao Lin
  • Zohreh Mostaani
  • Guillermo Ortiz Jimenez
  • Matteo Pagliardini
  • Scott Pesme
  • Aswin Suresh
  • Thijs Vogels
Student Assistants
  • Mohamed Ridha Chahed
  • Paul Griesser
  • Haitham Hammami
  • Wei Jiang
  • Stanislas Jouven
  • Maja Stamenkovic
  • Robin Zbinden
Lectures Tuesday 2x45mins youtube recordings
  Thursday 2x45mins youtube recordings
Q&A  Thursday 16:15 – 17:00 short live Q&A on zoom, about lecture contents
Exercises Thursday 14:15 – 16:00

Rooms: live on discord, or INF119INF2INJ218INM202INR219

Exercises Solutions Tuesday 17:15 – 18:00 live on zoom
Language:   English
Credits :   7 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: Wednesday 13.01.2021 from 16h15 to 19h15 in the SwissTech Convention Center
  • Please register on moodle asap so we can contact you. You can change registration later if needed.
  • The zoom links for Q&A and exercises (discord), the discussion forum, and the youtube playlist are on moodle.
  • Projects: There will be two group projects during the course.
    • Project 1 counts 10% and is due Oct 26th.
    • Project 2 counts 30% and is due Dec 17th.
  • The videos of the lectures for each week, new exercise sheet, as well as the solutions for the previous week will typically be made available each tuesday. Labs and projects will be in Python. See Lab 1 to get started.
  • Code Repository for Labs, Projects, Lecture notes:
  • Link to additional AriML online app (or iphone / android).
  • the exam is closed book but you are allowed one crib sheet (A4 size paper, both sides can be used), either handwritten or 11 point minimum font size; bring a pen and white eraser; you find the exams from the past three years with solutions here:

Detailed Schedule

Annotated lecture notes from each class are made available on github here.

Date Topics Covered Lectures Exercises Projects
15/9 Introduction, Linear Regression 01a,01b
17/9 Cost functions   Lab 1  
22/9 Optimization 02a    
24/9 Optimization   Lab 2 Project 1 start
29/10 Least Squares, Max Likelihood 03a,03b    
01/10 Overfitting, Ridge Regression, Lasso 03c,03d Lab 3  
06/10 Generalization, Model Selection, and Validation 04a    
08/10 Bias-Variance decomposition 04b Lab 4  
13/10 Classification 05a    
15/10 Logistic Regression 05b Lab 5  
20/10 Generalized Linear Models 06a    
22/10 K-Nearest Neighbor 06b Lab 6  
27/10 Support Vector Machines 07a   Proj. 1 due 26.10.
29/10 Kernel Regression 07b Lab 7  
03/11 Neural Networks – Basics, Representation Power 08a,08b   Project 2 start
05/11 Neural Networks – Backpropagation, Activation Functions 08c,08d Lab 8  
10/11 Neural Networks – CNN, Regularization, Data Augmentation, Dropout 09a,09b    
12/11 Adversarial ML 09c Lab 9  
17/11 Adversarial ML      
19/11 Unsupervised Learning, K-Means 10a,10b Lab 10  
24/11 Gaussian Mixture Models 11a    
26/11 EM algorithm 11b Lab 11  
01/12 Generative adversarial networks 12a    
03/12 SVD and PCA 12b Lab 12 & Q&A  
08/12 Matrix Factorizations 13a    
10/12 Text Representation Learning 13b Lab 13  
15/12 Projects      
17/12 Projects     Proj. 2 due 17.12.


(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

Final projects last year are done either in ML4Science in collaboration with any lab of EPFL, or the Reproducibility Challenge for ML papers, or one of the predefined ML challenges.

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