Note: The course materials are updated yearly to stay aligned with the latest research. The book will be useful for the TML23/24 course. However, it won’t cover new topics added to the course.
The registration link is here: https://forms.gle/NQ8ZgqZhZadkG1dq6. We start accepting registration from 29 September 2023 at 12:00 pm (noon) Central European Time (Berlin time).
Upon registration, you will get access to Exercise 0. The Exercise 0 is an individual exercise and will be based on the prerequisite materials for the course. Students who wish to enrol must submit their work on Exercise 0. The necessary prerequisite materials will be taught in the first lecture. Exercise 0 serves two purposes:
Submit Exercise 0 by 22 October 2023. If you do not submit Exercise 0, we’ll assume that you do not wish to register for the course and the exams.
The timeline for registration is as follows:
The final grade is essentially based on your exam performance. However, to encourage the participation in the exercises, we award top-ups on the final grade based on the exercise performance. We make sure, though, that it is still possible to get the maximal perfomance (grade 1,0) even without any top-up from the exercises.
Exercise 1-3 average score E (0 - 100%)
Admission to exam
Exam score X (0 - 100%)
Final score S (0 - 100%)
Final grade G (1,0 - 5,0)
Students may use language models for exercises. If you choose to do so, please follow the guideline below.
Please use the STAI group email
For those who’re registered for the course, ask the lecturer or tutors to add you to the Discord channel. We need your name and email address. Use it for
Lecture: Hörsaal N09 (Hörsaalzentrum Morgenstelle)
Tutorial: Hörsaal 7E02 (Hörsaalzentrum Morgenstelle)
|#||Date||Lecture content||Exercises||Tutorial session|
|-||29/09/2023||-||Exercise 0 (Due:22.10.2023) - Joon||No session|
|L1||16/10/2023||Introduction, OOD Generalisation (Definitions & evaluation) - Video||Exercise 1 (Due:12.11.2023) - Arnas||No session|
|L2||23/10/2023||OOD Generalisation (Definitions & evaluation, Cue selection) - Video||-||Q&A session|
|L3||30/10/2023||OOD Generalisation (Cue selection) - Video||-||Session for recap of Exercise 0 (Bálint) - Video|
|L4||06/11/2023||OOD Generalisation (Adversarial attacks) - Video||-||Q&A session|
|L5||13/11/2023||OOD Generalisation (Adversarial defenses), Explainability (Definitions) - Video||Exercise 2 (Due:10.12.2023) - Evgenii||Exercise 2 introduction|
|L6||20/11/2023||Explainability (Feature attribution) - Video||-||Session for recap of Exercise 1 (Arnas) - Video, Slides|
|L7||27/11/2023||Explainability (Feature attribution, Training data attribution) - Video||-||Co-working / Q&A|
|L8||04/12/2023||Explainability (Training data attribution) - Video||-||Co-working / Q&A|
|L9||11/12/2023||Uncertainty (Definitions & evaluation)||Exercise 3 (Due:28.01.2024) - Bálint||Exercise 3 introduction|
|L10||15/01/2024||Uncertainty (Aleatoric uncertainty)||-||Session for recap of Exercise 2 (Evgenii)|
|L11||22/01/2024||Uncertainty (Epistemic uncertainty)||-||Co-working / Q&A|
|L12||29/01/2024||Uncertainty (Foundational models), Conclusion||-||Co-working / Q&A|
|-||05/02/2024||-||-||Session for recap of Exercise 3 (Bálint)|