The course covers a number of machine learning methods and concepts, including state-of-the-art deep learning methods, with example applications in the medical imaging and computational biology domains.
This GitHub page contains all the general information about the course and the study materials. The Canvas page of the course will be used only for sharing of course information that cannot be made public (e.g. Microsoft Teams links), submission of the practical work and posting questions to the instructors and teaching assistants (in the Discussion section). The students are highly encouraged to use the Discussion section in Canvas. All general questions (e.g. issues with setting up the programming environment, error messages etc., general methodology questions) should be posted in the Discussion section.
TLDR: GitHub is for content, Canvas for communication and submission of assignments.
The course schedule is as follows:
- Lectures, general time: Wednesdays 08:45 - 10:45
- There is one exception: there is additional lecture on September 12 (Monday) and no lecture on September 21 (Wednesday).
- Guided self-study, time: Wednesdays 10.45 - 12.45
The practical work will be done in groups. The groups will be formed in Canvas and you will also submit all your work there (check the Assignments section for the deadlines). Your are expected to do this work independently with the help of the teaching assistants during the guided self-study sessions (begeleide zelfstudie). You can also post your questions in the Discussion section in Canvas at any time (i.e. not just during the practical sessions).
IMPORTANT: Please read this guide on effectively asking questions during the practical sessions.
The lectures are mainly based on the selected chapters from the following two books that are freely available online:
- Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville
- Elements of Statistical Learning, Trevor Hastie, Robert Tibshirani, Jerome Friedman
The follwing book is optional but highly recommended:
- Probabilistic Machine Learning: An Introduction, Kevin Patrick Murphy.
Additional reading materials such as journal articles are listed within the lecture slides.
IMPORTANT: It is essential that you correctly set up the Python working environment by the end of the first week of the course so there are no delays in the work on the practicals.
The practical assignments for this course will be done in Python. Please carefully follow the instructions available here on setting up the working environment and (optionally) a Git workflow for your group.
IMPORTANT: Attempting the quiz before the specified deadline is mandatory.
In the first week of the course you have to do a Python self-assessment quiz in Canvas. The quiz will not be graded. If you fail to complete the quiz before the deadline, you will not get a grade for the course. The goal of the quiz is to give you an idea of the Python programming level that is expected.
If you lack prior knowledge of the Python programming language, you can use the material in the "Python essentials" and "Numerical and scientific computing in Python" modules available here.
**IMPORTANT: The course is lightly restructured from the 2021 edition. However, the materials (lectrue slides and practical work assignments) will largely be unchanged. Links to the updated materials will be added to the table below as the course progresses. If you want a sneak peek, the materials from the 2021 edition of the course are available here.
| # | Date | Title | Slides |
|---|---|---|---|
| 1 | 07/Sep | Machine learning fundamentals | intro, slides, extended |
| 2 | 12/Sep (:exclamation:) | Linear models | slides |
| 3 | 14/Sep | Support vector machines, random forests | slides |
| 4 | 28/Sep | Deep learning I | slides |
| 5 | 05/Oct | Deep learning II | slides, transformers intro |
| 6 | 12/Oct | Unsupervised machine learning | slides |
| 7 | 19/Oct | Transformers | slides |
| 8 | 26/Oct | (Guest lecture) Explainable AI by Francesca Grisoni, not included in the exam 👍 | slides |
| 🔺 | 02/Nov | Exam | Example exam |
| # | Date | Title | Slides |
|---|---|---|---|
| 1 | 07/Sep | Machine learning fundamentals I | exercises |
| 1 | 14/Sep | Machine learning fundamentals II | exercises |
| 3 | 21/Sep | Linear models | exercises |
| 4 | 28/Sep | Support vector machines, random forests | exercises |
| 5 | 05/Oct | Deep learning I | exercises |
| 6 | 12/Oct | Deep learning II | exercises in Google Colab |
| 7 | 19/Oct | Catch up week! 🍅 | - |
After completing the course, the student will be able to:
- Recognise how machine learning methods can be used to solve problems in Medical Imaging and Computational Biology.
- Comprehend the basic principles of machine learning.
- Implement and use machine learning methods.
- Design experimental setups for training and evaluation of machine learning models.
- Analyze and critically evaluate the results of experiments with machine learning models.
The assessment will be performed in the following way:
- Work on the practical assignments: 25% of the final grade (each assignment has equal contribution);
- Reading assignment: 10% of the final grade;
- Final exam: 65% of the final grade.
Intermediate feedback will be provided as grades to the submitted assignments.
The grading of the assignments will be done per groups, however, it is possible that individual students get separate grade from the rest of the group (e.g. if they did not sufficiently participate in the work of the group).
An example exam can be found here.
The students will receive instruction in the following ways:
- Lectures
- Guided practical sessions with the teaching assistants for questions, assistance and advice
- On-line discussion
Course instructors:
- Mitko Veta
- Federica Eduati
Teaching assistants:
- Oscar Lapuente Santana
- Rens ter Maat
- Hassan Keshvarikhojasteh
8DB00 Image acquisition and Processing, and 8DC00 Medical Image Analysis.
This page is carefully filled with all necessary information about the course. When unexpected differences occur between this page and Osiris, the information provided in Osiris is leading.