This is the OLD 2016 course website. For the current one, see here.
This course is offered jointly with the Information Processing Group. (Course formerly known as Pattern Classification and Machine Learning).
Previous year’s website: http://icapeople.epfl.ch/mekhan/pcml15.html
Our contact email: [email protected]
Instructor | Martin Jaggi | Instructor | Ruediger Urbanke | |
Office | INJ 341 | Office | INR 116 | |
Phone | +41 21 69 37059 | Phone | +41 21 69 37692 | |
[email protected] | [email protected] | |||
Office Hours | By appointment | Office Hours | By appointment |
Teaching Assistant | Mohamad Dia | [email protected] | Office | INR 140 | ||
Teaching Assistant | Ksenia Konyushkova | [email protected] | Office | BC304 | ||
Teaching Assistant | Victor Kristof | [email protected] | Office | BC204 | ||
Teaching Assistant | Taylor Newton | [email protected] | Office | B1 Geneva | ||
Teaching Assistant | Farnood Salehi | [email protected] | Office | BC250 | ||
Teaching Assistant | Benoît Seguin | [email protected] | Office | INN 140 | ||
Student Assistant | Frederik Kunstner | [email protected] | ||||
Student Assistant | Fayez Lahoud | [email protected] | ||||
Student Assistant | Tao Lin | [email protected] | ||||
Student Assistant | Arnaud Miribel | [email protected] | ||||
Student Assistant | Vidit Vidit | [email protected] |
Lectures | Tuesday | 8:15 – 10:00 (Room: CE1) |
Thursday | 8:15 – 10:00 (Room: CE4) | |
Exercises | Thursday | 14:15 – 16:00 (Room: INF119,INJ218,INM11,INM202) |
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
F Fuentes => H (HWANG) — SALLE POLYVALENTE (2nd floor)
R (Radovanovic) to Z (Zoss) — CE 1
-
The new exercise sheet, as well as the solution (code only) for last weeks lab session will typically be made available each tuesday (here and on 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 22nd.
-
-
All Labs and Projects will be in Python this year. See Lab 1 to get started.
-
Code Repository for Labs, Projects, Lecture notes: github.com/epfml/ML_course
-
Lectures: Clicker: For some active participation in the lectures, please point your browser to this speak-up room
-
Lecture notes: We provide PDF lecture notes here below and also on Nota Bene so you can comment & discuss them.
Detailed Schedule
(tentative, subject to changes)
Annotated lecture notes from each class are made available on github here.
Date | Topics Covered | Lectures | Exercises | Projects |
---|---|---|---|---|
20/9 | Introduction | 01a,01b | ||
22/9 | Linear Regression, Cost functions | 01c,01d | Lab 1 | |
27/9 | Optimization | 02a | ||
29/9 | Optimization | Lab 2 | ||
04/10 | Least Squares, ill-conditioning, Max Likelihood | 03a,03b | Project 1 details | |
06/10 | Overfitting, Ridge Regression, Lasso | 03c,03d | Lab 3 | |
11/10 | Cross-Validation | 04a | ||
13/10 | Bias-Variance decomposition | 04b | Lab 4 | |
18/10 | Classification | 05a | ||
20/10 | Logistic Regression | 05b | Lab 5 | |
25/10 | Generalized Linear Models | 06a | ||
27/10 | K-Nearest Neighbor | 06b | Q&A for proj. | |
01/11 | Support Vector Machines | 07a | Proj. 1 due 31.10. | |
03/11 | Kernel Regression | 07b | Lab 7 | |
08/11 | Unsupervised Learning, K-Means | 08a,08b | ||
10/11 | K-Means, Gaussian Mixture Models | 08c | Lab 8 | |
15/11 | Mock Exam | |||
17/11 | Gaussian Mixture Models, EM algorithm | 09a | Mock exam&sol. | Project 2 details |
22/11 | Matrix Factorizations | 10a | ||
24/11 | Text Representation Learning | 10b | Lab 10 | |
29/11 | SVD and PCA | 11a | ||
01/12 | SVD and PCA/Neural Networks – Basics | 12a | Lab 11 | |
06/12 | Neural Networks – Representation Power | 12b | ||
08/12 | Neural Networks – Backpropagation, Activation Functions | 12c,12d | Q&A for proj. | |
13/12 | Neural Networks – CNN, Regularization, Data Augmentation, Dropout | 12e,12f | ||
15/12 | Graphical Models — Bayes Nets | 13a | Lab 13 | |
20/12 | Graphical Models — Factor Graphs | 14a, FG | ||
22/12 | Graphical Models — Inference and Sum-Product Algorithm | Lab 14 | Project 2 due |
Textbooks
Christopher Bishop, Pattern Recognition and Machine Learning
Kevin Murphy, Machine Learning: A Probabilistic Perspective
Shai Shalev-Shwartz, Shai Ben-David, Understanding Machine Learning