This course is offered jointly by the TML and MLO groups. Previous year’s website: ML 2021.
See here for 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 protected]||[email protected]|
|Office Hours||By appointment||Office Hours||By appointment|
|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||
(assignment see course info sheet)
|Credits :||8 ECTS|
- Exam Date: Friday 20.01.2023 from 15h15 to 18h15 in SwissTech
- The links for the exercises signup and the discussion forum password are on moodle. 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 Oct 31st.
Project 2 counts 30% and is due Dec 22th.
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:
|20/9||Introduction, Linear Regression||01a,01b
|21/9||Cost functions||Lab 1|
|28/9||Optimization||Lab 2||Project 1 start|
|04/10||Least Squares, Overfitting||03a,03b|
|05/10||Max Likelihood, Ridge Regression, Lasso||03c,03d||Lab 3|
|11/10||Generalization, Model Selection, and Validation||04a||04a|
|12/10||Bias-Variance decomposition||04b||04b||Lab 4|
|19/10||Logistic Regression||05b||05b||Lab 5|
|25/10||Generalized Linear Models||06a||06a|
|26/10||K-Nearest Neighbor||06b||06b||Lab 6|
|01/11||Support Vector Machines||07a||07a||Proj. 1 due 31.10.|
|02/11||Kernel Regression||07b||07b||Lab 7|
|08/11||Neural Networks – Basics, Representation Power||08a,08b||08ab||Project 2 start|
|09/11||Neural Networks – Backpropagation, Activation Functions||08c,08d||08cd||Lab 8|
|15/11||Neural Networks – CNN, Regularization, Data Augmentation, Dropout||09a,09b||09ab|
|16/11||Adversarial ML||09c||09c||Lab 9|
|22/11||Ethics and Fairness in ML||10a|
|23/11||Unsupervised Learning, K-Means||10b,10c||Lab 10|
|29/11||Gaussian Mixture Models||11a|
|30/12||EM algorithm||11b||Lab 11|
|07/12||SVD and PCA||12b||Lab 12 & Project Q&A|
|13/12||Guest Lecture on Sustainability in AI, by Roy Schwartz||slides|
|14/12||Matrix Factorizations||13a||Lab 13|
|20/12||Text Representation Learning||14a|
|21/12||Projects pitch session (optional)||Proj. 2 due 22.12.|
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 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.