VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

263-5210-00L 8 Credits BSC , MSC , WBZ D-MAVT , D-INFK , D-MATH , D-PHYS , D-ERDW , D-ITET , D-BSSE

Probabilistic Artificial Intelligence

Lecturers & Examiners: Prof. Dr. Andreas Krause
VVZ CR 4.01

Last Updated: 2026-06-03 00:07:33

Abstract

This 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.

Objective

How 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.

Content

Topics 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

General Information

Language
English
Levels
BSC , MSC , WBZ
Frequency
Yearly recurring

Examination

Type
session examination
Mode
written 120 minutes
Aids
Two A4-pages (i.e. one A4-sheet of paper), either handwritten or 11 point minimum font size. Simple non-programmable calculator.
Digital
The exam takes place on devices provided by ETH Zurich.
100% of the final grade is determined by the session examination. As a compulsory continuous performance assessment task, the project component of the course must be passed on it's own to take the exam.The practical projects are an integral part (60 hours of work, 2 credits) of the course.The project component is assessed on a pass/fail basis. Participation is mandatory.Failing the project results in a failing grade for the overall examination of Probabilistic Artificial Intelligence (263-5210-00L).Students who do not pass the project component are required to de-register from the exam and will otherwise be treated as a no show.Due to the number of registered students, the exam may be paper-based and will most likely take place on a Saturday. The mode of the exam (computer-based or paper-based) will be finalized in end of October, and the exam date will be announced in December.

Registration & Places

Max Places
900

Course Components

Type Title Time & Place Hours
lecture Probabilistic Artificial Intelligence
Fr 10-12 und 13-14 im ETA F5 mit Videoübertragung ins ETF E1
No time listed 3 h weekly
exercise Probabilistic Artificial Intelligence
Q&A session via zoom
No time listed 2 h weekly
independent project Probabilistic Artificial Intelligence No time listed 2 h weekly

Offered In