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 protected]||[email protected]|
|Office Hours||By appointment||Office Hours||By appointment|
|Q&A||Thursday||16:15 – 17:00||short live Q&A on zoom, about lecture contents|
|Exercises||Thursday||14:15 – 16:00|
|Exercises Solutions||Tuesday||17:15 – 18:00||live on zoom|
|Credits :||7 ECTS|
- 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: 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), 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:
Annotated lecture notes from each class are made available on github here.
|15/9||Introduction, Linear Regression||01a,01b
|17/9||Cost functions||Lab 1|
|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|
|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|
|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|
|10/12||Text Representation Learning||13b||Lab 13|
|17/12||Projects||Proj. 2 due 17.12.|
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
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.