Exercise sessions
Use this link to ask for help during zoom exercise sessions. Links to an external site.
Zoom link for computer session Links to an external site.
During the course, 10 exercise sessions are offered. For most topics, there is both a pen-and-paper session (pp) and a computer session (c). Each session is offered at two different time slots in the schedule. We hope that the students will be evenly distributed among the sessions, but you can choose which session to attend. For the computer sessions, it will also be possible to attend via Zoom (further details will be announced).
During each exercise session, the teacher will present a summary of the material covering the specific topic, after which you are expected to work on the problems on your own. We recommend attempting to solve the problems beforehand, and taking the opportunity to ask questions and discuss the problems with the teacher and your fellow students during the exercise sessions. A few of the problems are listed as recommended, but we encourage you to read and reflect upon all problems (even if you do not solve them).
L0 (optional): Python introduction
L0 is an optional exercise session intended as an introduction to Python for students who needs a warm-up before the programming part of the course. Please watch the recorded lecture before the exercise session. You can find links to the accompanying notebook and a video crashcourse on the lecture page. During the exercise session, we will work with the exercises listed in the table below. You can work directly with the exercises online through the cloud platform Google Colab. If you choose to work locally on your own computer, be sure to have Python installed and your environment set up for running the notebooks before the exercise session.
| # | Topic | Material | Recommended problems |
Additional problems |
| 0. | Python Introduction (optional) |
Notebook Links to an external site. |
- | - |
| 1. | Linear Regression (pp) | 1, 2, 3 | 4, 5 | |
| 2. | Linear Regression (c) |
Notebook Links to an external site. |
1, 2, 3, 4 | 5 |
| 3. | Logistic Regression, LDA, QDA, kNN (pp) | 1, 2, 3, 5 | 4, 6, 7 | |
| 4. | Logistic Regression, LDA, QDA, kNN (c) |
Notebook Links to an external site. |
1, 2, 3, 4 | 5 |
| 5. | Bias and variance, model selection, cross validation (pp) | 1, 2, 3, 4 | 5, 6 | |
| 6. | Bias and variance, model selection, cross validation (c) |
Notebook Links to an external site. |
1, 2, 3 | 4 |
| 7. | Tree-based methods (pp) | Session7.pdf Links to an external site. |
1, 2, 3, 4 | |
| 8. | Tree-based methods (c) |
Notebook Links to an external site. |
1, 2 | 3 |
| 9. | Boosting (c) |
Notebook Links to an external site. |
1, 2, 3 | 4, 5 |
| 10. | Neural Networks (pp) | 1, 2, 3, 4 |
pp = pen and paper, c = computer