# CS-433 | CS-433 Machine Learning

https://epfml.github.io/cs433-2025

[CS-433 Machine Learning](https://epfml.github.io/cs433-2025)
  * [Course info](https://epfml.github.io/cs433-2025/courseinfo)
  * [ML4Science](https://epfml.github.io/cs433-2025/ml4science)
  * [ Search ](https://epfml.github.io/cs433-2025/ "Search")


✕
# CS-433
* * *
Machine Learning
# Machine Learning (CS-433)
Previous year’s website: [ML 2024](https://www.epfl.ch/labs/mlo/machine-learning-cs-433-2024/).  

**Contact:** Use the **[discussion forum](https://edstem.org/eu/courses/2577)**.
**Instructors:** Bob West
## Logistics
  * **Lectures**
    * **Tue** 16:15–18:00 — Rolex Learning Center
    * **Wed** 10:15–12:00 — Rolex Learning Center
  * **Exercises** **Thu** 14:15–16:00 Rooms: ~~INF1~~ , INF119, INJ218, INM202, CO123, INR219
  * **Language:** English
  * **Credits:** 8 ECTS
  * **Info sheet:** **[Course info](https://epfml.github.io/cs433-2025/courseinfo)**
  * **Official catalog:** **[EPFL coursebook](https://edu.epfl.ch/coursebook/en/machine-learning-CS-433)**


* * *
## Special Announcements
  * **Exam:** Thursday, 15 January 2026, 15h15 - 18h15
  * **Projects:** two group projects 
    * Project 1 — **10%** , **due October 31**.
    * Project 2 — **30%** , **due December 18**.
  * **Videos:** weekly lecture videos on **[Mediaspace](https://mediaspace.epfl.ch/channel/CS-433+Machine+learning)**. 
    * [Link to tuesday live sessions](https://mediaspace.epfl.ch/media/0_eis8becm)
    * [Link to wednesday live sessions](https://mediaspace.epfl.ch/media/0_b2ps30nk)
  * **Code & material:** **[epfml/ML_course](https://github.com/epfml/ML_course)**.
  * **Exam format:** closed book; one A4 **crib sheet** (both sides).  
Past exams (+ solutions): **[2016–2023](https://github.com/epfml/ML_course/tree/main/exam)**.


* * *
## Schedule & Materials
Note that this schedule is only approximative. We’ll go through the material in the order listed here, but it might well be that certain materials will be reached earlier or later than listed here.
Slides will be made available on GitHub.  
| Date  | Topic (lectures)  | Labs  | Projects  |  
| --- | --- | --- | --- |  
| 09/9  | Introduction, Regression, Linear Regression  |   |   |  
| 10/9  | Loss Functions, Optimization  | **[Lab 1](https://github.com/epfml/ML_course/tree/main/labs/ex01)**  |   |  
| 16/9  | (cont’d)  |   |   |  
| 17/9  | (cont’d)  | **[Lab 2](https://github.com)**  | **[Project 1 start](https://github.com)**  |  
| 23/9  | Least Squares, Overfitting  |   |   |  
| 24/9  | ML Estimation, Ridge, Lasso  | **[Lab 3](https://github.com)**  |   |  
| 30/09  | Generalization & Model Selection  |   |   |  
| 1/10  | (cont’d)  | **[Lab 4](https://github.com)**  |   |  
| 7/10  | Classification  |   |   |  
| 8/10  | Logistic Regression  | **[Lab 5](https://github.com)**  |   |  
| 14/10  | Support Vector Machines  |   |   |  
| 15/10  | k Nearest Neighbors  | **[Lab 6](https://github.com)**  |   |  
| 28/10  | Kernel Regression  |   |   |  
| 29/10  | Neural Nets: Basics & Rep. Power  | **[Lab 7](https://github.com)**  |   |  
| **31/10**  |   |   | **Project 1 due**  |  
| 04/11  | Backprop & Activations  |   | **[Project 2 start](https://github.com)**  |  
| 05/11  | Convolutional Neural Networks, Regularization, Augmentation, Dropout  | **[Lab 8](https://github.com)**  |   |  
| 11/11  | Transformers  |   |   |  
| 12/11  | Adversarial ML  | **[Lab 9](https://github.com)**  |   |  
| 18/11  | Ethics & Fairness in ML  |   |   |  
| 19/11  | Unsupervised Learning (K-Means, GMMs)  | **[Lab 10](https://github.com)**  |   |  
| 25/11  | Expectation Maximization Algorithm  |   |   |  
| 26/11  | Matrix Factorization  | **[Lab 11](https://github.com)**  | Project Q&A  |  
| 02/12  | Text Representation Learning  |   |   |  
| 03/12  | Large Language Models  | **[Lab 12](https://github.com)**  | Project Q&A  |  
| 09/12  | Self-Supervised Learning  |   |   |  
| 10/12  | Genervative Models (GANs, Diffusion)  | **[Lab 13](https://github.com)**  |   |  
| 16/12  | Outlook: Some reflections on steering AI to do what we want it to do  |   |   |  
| 17/12  | (No class)  |   | **Project 2 due 18/12**  |  
* * *
## Textbooks (optional)
  * 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_


* * *
## Teaching Team
**Teaching Assistants**  
Alexander Hägele • Atli Kosson • Dongyang Fan • Francesco D’Angelo • Gizem Yüce • Hristo Papazov • Oguz Yüksel • Bettina Messmer • Diba Hashemi • Justin Samuel Deschenaux • Mohammad Hossein Amani • Saibo Geng
**Student Assistants**  
Adam Mesbahi Amrani • Ahyoung Seo • Efe Tarhan • Eren Akçanal • Francesco Bellotto • Igor Pavlović • Jacques Mandriota • Jingxuan Sun • Leonardo Martella • Michele Lanfranconi • Mikulas Vanousek • N’Zian Cédric Koffi • Shunchang Liu • Vincenzo Sigillo’ Massara • Xinran Li • Yassine Mustapha Wahidy • Zhuofu Zhou
  * Email me


CS-433 team • 2025 • [Edit page](https://github.com/epfml/epfml.github.io/edit/main/cs433-2025/index.md "Edit this page on GitHub")
Powered by [Beautiful Jekyll](https://beautifuljekyll.com)