Syllabus

Lecturers: Michael Muehlebach, Bernhard Schölkopf, Andreas Krause

Course code: 263-5156-00L

Abstract: Many machine learning problems go beyond supervised learning on independent data points and require an understanding of the underlying causal mechanisms, the interactions between the learning algorithms and their environment, and adaptation to temporal changes. The course highlights some of these challenges and relates them to state-of-the-art research.

Objective: The goal of this seminar is to gain experience with machine learning research and foster interdisciplinary thinking.

Content: The seminar will be divided into two parts. The first part summarizes the basics of statistical learning theory, game theory, causal inference, and dynamical systems in four lectures. This sets the stage for the second part, where distinguished speakers will present selected aspects in greater detail and link them to their current research.

Keywords: Causal inference, adaptive decision-making, reinforcement learning, game theory, meta learning, interactions with humans

Prerequisites: B.Sc. in computer science or related field (engineering, physics, mathematics). Passed at least one learning course, such as “Introduction to Machine Learning” or “Probabilistic Artificial Intelligence”.

Number of Credits: 2 KP

Scope: Seminar (1.5 hours per week)

Schedule: Wednesdays from 16:15–18:00

Examination: Performance assessment (pass/fail) will take place in the last week of the seminar. The details will be announced during the first lecture.

Teaching Assistants: Maximilian Mordig, Timothy Gebhard