Andreas Krause: Catalogue data in Autumn Semester 2021

Award: The Golden Owl
Name Prof. Dr. Andreas Krause
FieldComputer Science
Address
Institut für Maschinelles Lernen
ETH Zürich, OAT Y 13.1
Andreasstrasse 5
8092 Zürich
SWITZERLAND
Telephone+41 44 632 63 22
Fax+41 44 623 15 62
E-mailkrausea@ethz.ch
URLhttp://las.ethz.ch/krausea.html
DepartmentComputer Science
RelationshipFull Professor

NumberTitleECTSHoursLecturers
252-0945-13LDoctoral Seminar Machine Learning (HS21)
Only for Computer Science Ph.D. students.

This doctoral seminar is intended for PhD students affiliated with the Institute for Machine Learning. Other PhD students who work on machine learning projects or related topics need approval by at least one of the organizers to register for the seminar.
2 credits1SJ. M. Buhmann, N. He, A. Krause, G. Rätsch, M. Sachan
AbstractAn essential aspect of any research project is dissemination of the findings arising from the study. Here we focus on oral communication, which includes: appropriate selection of material, preparation of the visual aids (slides and/or posters), and presentation skills.
ObjectiveThe seminar participants should learn how to prepare and deliver scientific talks as well as to deal with technical questions. Participants are also expected to actively contribute to discussions during presentations by others, thus learning and practicing critical thinking skills.
Prerequisites / NoticeThis doctoral seminar of the Machine Learning Laboratory of ETH is intended for PhD students who work on a machine learning project, i.e., for the PhD students of the ML lab.
263-5156-00LBeyond iid Learning: Causality, Dynamics, and Interactions Information Restricted registration - show details
Number of participants limited to 60.

The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.
2 credits2SM. Mühlebach, A. Krause, B. Schölkopf
AbstractMany 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.
ObjectiveThe goal of this seminar is to gain experience with machine learning research and foster interdisciplinary thinking.
ContentThe 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.
Lecture notesFurther information will be published on the course website: https://beyond-iid-learning.xyz/
Prerequisites / NoticeBSc 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".
263-5210-00LProbabilistic Artificial Intelligence Information Restricted registration - show details 8 credits3V + 2U + 2AA. Krause
AbstractThis course introduces core modeling techniques and algorithms from machine learning, optimization and control for reasoning and decision making under uncertainty, and study applications in areas such as robotics.
ObjectiveHow can we build systems that perform well in uncertain environments? How can we develop systems that exhibit "intelligent" behavior, without prescribing explicit rules? How can we build systems that learn from experience in order to improve their performance? We will study core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as robotics. The course is designed for graduate students.
ContentTopics covered:
- Probability
- Probabilistic inference (variational inference, MCMC)
- Bayesian learning (Gaussian processes, Bayesian deep learning)
- Probabilistic planning (MDPs, POMPDPs)
- Multi-armed bandits and Bayesian optimization
- Reinforcement learning
Prerequisites / NoticeSolid basic knowledge in statistics, algorithms and programming.
The material covered in the course "Introduction to Machine Learning" is considered as a prerequisite.