Probabilistic Artificial Intelligence (2026)

How can we build systems that perform well in uncertain environments and unforeseen situations? 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 sensor networks, robotics, and the Internet. The course is designed for upper-level undergraduate and graduate students. VVZ information is available here.

News

• • [17.09.2026] Due to high enrollment, during Week 1 only, students with even Legi numbers should attend the lecture in ETA F5 and students with odd Legi numbers in ETF E1; from Week 2 onward, you may attend either lecture hall subject to available space.
  • [11.09.2026] The first lecture of the course will begin on Friday, 18th September as specified in the schedule below. The first tutorial will be on Thursday, 24th September.

Access to lecture materials

The lecture materials and the Q&A zoom meetings are password protected. To obtain the password you need to be inside the ETH network or use the ETH VPN and click here. Check here to learn how to establish a VPN connection.

---

Script

The lecture script is available here. If you find mistakes or have suggestions for improving the script, please post them in the respective Moodle forum. We aim to continuously improve the script based on your feedback. Since the script is updated whenever we notice and fix a mistake, we encourage you to re-download it from time to time. Errors noticed since the beginning of the semester will be listed in the errata at the end of the PDF. You can check which errors have been fixed since your version of the script by comparing the compilation date on page (ii).

---

Lectures

Lectures will be held on Fridays, 10:15 to 12:00 and 13:15 to 14:00, in ETA F5 with a simultaneous video transmission to ETA E1. If you are in ETA E1, you will be able to ask questions via the course channel on the EduApp. The Lectures are not live-streamed. They are recorded and the recording will be made available after the lecture (a link will be added here once the first lecture becomes available). It is not mandatory, but very much encouraged, to attend the lectures. The table below will be filled as the resource becomes available. The lecture materials and recordings from last year’s course are available on last year’s course website.

---

Tutorials

Tutorials will be held on Thursdays, 16:15 to 18:00 in HG F7. The tutorials are also not live-streamed but recorded and also available afterwards on this webpage. It is not mandatory, but very much encouraged, to attend the tutorials. The last tutorial session is a review of the specific lecture content in preparation for the exam.

---

Q&A sessions

Q&A sessions (virtual office hours) will be held on Monday, 17:15 to 18:00 virtually on Zoom. To join the Zoom call, you have to be logged into your ETH zoom account (i.e., <nethz-login>@ethz.ch and your email password) and enter the Zoom room password. The session will be recorded and the recording will be made available afterwards. The Q&A sessions are an informal opportunity to ask questions about the course. You will be able to ask questions via the native Zoom chat or by speaking out. In the Q&A sessions occurring on the day a new task is released, we will give a brief overview of the new task, and sketch possible solutions for the previous task. In the Q&A sessions occurring one week after task release, we will also be there to answer any questions related to the project. It is not mandatory to attend the Q&A sessions. These sessions will be recorded and the recording will be made available after the session on this webpage.

---

---

Moodle

We kindly ask you to use Moodle to ask questions with regard to the course. Please ask your questions in the Moodle forum whose topic best fits your question. In special cases, if you need to contact the Head TA directly, please send an email to pai26-info@inf.ethz.ch instead of contacting them at their personal email address. The head TA will not respond to requests sent to their personal email address. Please think twice before you send an email though and make sure you read all information here carefully. Based on previous experience, we received a lot of questions or requests that are resolvable with the information provided here.

Projects

The course includes a total of five projects. Projects are code assignments that require solving machine learning problems with methods taught in the course. For each project, you are allowed to work in a group of one to three students. It is your own responsibility to form a group and you can find teammates in the lectures or on Moodle. The first project (Task 0) will be ungraded; its purpose is to help you familiarize yourself with the code submission workflow. The remaining projects are graded and you are required to pass 3 out of 4 of them in order to be eligible to sit the exam. More information including a tentative schedule is available in the project information sheet and on the project server. The project server is accessible from within the ETH network or via VPN.

Homework

We will publish a total of six (optional) homework assignments during the lecture series. The homework assignments will be published on this website and some questions from the homework assignment will additionally be made available as a Moodle quiz. These assignments are intended for you to apply and reinforce the material presented in the lecture and to get accustomed to the Moodle platform. You are encouraged, but not required to do the homework. Your performance in the homework will have no influence on your final grade. Homework assignments are expected to be published bi-weekly, with solutions following one week after or being directly visible in Moodle. The exact day and time a homework is being published may deviate slightly over the course of the semester.

Demos

Demos will be shown during the lecture and are made available to you here. They are hosted in a GitLab repository to which you need to be given access. Everyone who enrolled (on mystudies) to the course before October 1st 2026, will be automatically granted access to this Gitlab repository. If you enrolled at a later date, please individually request access by sending an email to pai26-info@inf.ethz.ch. Use the subject line “Access Request: PAI 2026 Demos” and include your nethz in this email. The demos are Jupyter Notebooks.

---

Ethel (chat assistant)

This semester, we are again using the chat assistant called Ethel. Ethel is intended to help answer questions about the course material and is specifically conditioned on the content of Probabilistic Artificial Intelligence. The bot uses retrieval augmented generation (RAG) on top of state-of-the-art LLMs to provide responses aligned with the material of our course.

Like ChatGPT and others, however, Ethel is a language model that can provide incorrect or unexpected answers. While we take no responsibility for its responses, we think Ethel may be a valuable, complementary study tool and more suitable than general-purpose assistants. We appreciate your feedback on Moodle. By using Ethel, you acknowledge and agree to the following disclaimers and limitations.

---

Exam

We will provide further information on the exam later during the semester.

---

Repetition Exam: We hold an exam in the winter during the Examination Session, and we do not offer a repetition exam in summer. You will need to enrol next year, if you fail to participate in the winter exam or fail to obtain a passing grade.

---

Study resources for the exam: You can download the exams from the previous years with provisional solutions: [Exam-2021-A] [Solution-2021-A] [Exam-2021-B] [Solution-2021-B] [Exam-2022-A] [Solution-2022-A] [Exam-2022-B] [Solution-2022-B] [Exam-2023] [Solution-2023] [Exam-2024] [Solution-2024] [Exam-2025] [Solution-2025] [Exam-2026] [Solution-2026], to better prepare yourself for the final exam. Please note that we do not guarantee 100% correctness of the provided solutions. You are encouraged to think for yourself and discuss exam-related content on the Moodle forum or share any questions. Any exams that are older are not fully representative of the course content, because the course changed substantially five years ago. In case you still do want to take a look at them, please refer to the course webpage of PAI 2020, where you can access exam sheets from 2012 to 2019.

---

Performance Assessment

In order to be allowed to sit the session examination, you need to pass the projects. This year, that means achieving a grade of pass on 3 out of the 4 graded projects (not including task 0). If you don’t pass the projects, you are required to de-register from the exam and will otherwise be treated as a no-show. The final grade for the course will be 100% based on your exam grade. There are no special arrangements for PhD students who are taking this course. In order to obtain a “Testat”, you need a passing grade for the course. That is, you need to pass the projects as described above, take the exam and achieve a passing grade (4 or higher) for the course. If you passed the projects last year, you still need to do the projects again this year. The project grade cannot be carried over from the previous year.

Text Books

• • • S. Russell, P. Norvig. Artificial Intelligence: A Modern Approach (4th edition).
    • C. E. Rasmussen, C. K. I. Williams Gaussian Processes for Machine Learning.
    • Christopher M. Bishop. Pattern Recognition and Machine Learning. [optional]
    • Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction.