Scientific Machine Learning

URL study guide

https://studiegids.vu.nl/en/courses/2025-2026/XM_0138

Course Objective

Upon completion of this course, students will:be acquainted with the dominant concepts of machine learning methods, including some theoretical background. (Knowledge and understanding)acquire knowledge of established machine learning techniques such as linear models, neural networks, decision trees and ensemble methods (Knowledge and understanding)learn some statistical techniques to assess and validate machine learning results. (Apply knowledge and understanding, make judgments)have worked with a scientific data set related to bioinformatics to define and solve a relevant scientific ML and biological question (Apply knowledge and understanding, make judgement and communicate with fellow students and teachers)

Course Content

Machine learning is the discipline that studies how to build computer systems that learn from experience. It is a subfield of artificial intelligence that intersects with statistics, cognitive science, information theory, and probability theory. Recently, machine learning has become increasingly important for the design of search engines, robots, and sensor systems, and for the processing of large scientific data sets. It has also become increasingly important to tackle bioinformatics questions related to diseases, molecular interactions, and molecular property predictions. The course covers a wide variety of machine learning techniques, but puts particular emphasis on gradient descent optimization, backpropagation, neural networks and deep learning. Some discussion on the broader social impact of machine learning technology is included. During the practical part, students will work together on real world data sets from cancer research, protein-protein interactions, protein aggregation and solubility, or small bio-active molecules. Instead of focusing solely on improving model prediction, the ML methods are leveraged to investigated the provided data sets and gain a better understanding of the underlying biological problems.

Teaching Methods

The course evaluation consists of two parts: an examination and a practical assignment (50%). The examination consists of a standard exam (50%) and four online quizzes (pass/fail
- required for the exam). The examination is supported by pre-recorded videos, interactive lecture/QA sessions (two per week) and optional homework assignments discussed in working groups (one per week). The practical assignment is supported by small exercises to help with the relevant technologies, and informal presentations at project groups (one per week). There is no mandatory attendance for any lectures, however, the weekly project group meetings are mandatory for all group members to actively participate in the discussion of the other presented group projects. Every student is allowed to skip one group project session, as long as at least one member of the group is present during the project group. A large amount of the material is freely available at http://mlvu.github.io The course is taught in English.

Method of Assessment

The examination and practical assignment both comprise 50% of the final grade. To pass the course, the examination grade should be at least 5.5, the practical assignment grade should be at least 5.5 and the average should be at least 5.5. The examination is made individually, and the practical assignment is made in groups of 5. There is a resit for the exam, no resit is possible for the practical assignment.

Literature

There is no textbook. Some reading material will be provided digitally.

Target Audience

The course project uses a selection of preprocessed data sets tailored for the Master Bioinformatics and Systems Biology. Please note that students who completed Machine Learning (X_400154) as part of their Bachelor programme, or who completed this course during the Master before 2024-2025, are not allowed to take Scientific Machine Learning (XM_0138) as part of their Master programme.

Custom Course Registration

Working group registration will be done through Canvas in the first week of the course. Only a registration for the main course itself is required to take part in all parts of the course.

Recommended background knowledge

We require that students have some prior experience with linear algebra, calculus (limited to differentiation), and probability theory or statistics. A basic understanding will suffice and we will take some time to go over the basics again. Feel free to register if you have no experience with any of these, but expect to put in a little extra effort in the first weeks (using the materials provided). Programming experience, preferably in Python, is highly recommended. For the project, an interest in bioinformatics-related topics such as cancer research, protein-protein interactions, protein aggregation and solubility, or small bioactive molecules is highly recommended.