263-2400-00L  Reliable and Trustworthy Artificial Intelligence

SemesterAutumn Semester 2021
LecturersM. Vechev
Periodicityyearly recurring course
Language of instructionEnglish


AbstractCreating reliable and explainable probabilistic models is a fundamental challenge to solving the artificial intelligence problem. This course covers some of the latest and most exciting advances that bring us closer to constructing such models.
ObjectiveThe main objective of this course is to expose students to the latest and most exciting research in the area of explainable and interpretable artificial intelligence, a topic of fundamental and increasing importance. Upon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of problems.

To facilitate deeper understanding, an important part of the course will be a group hands-on programming project where students will build a system based on the learned material.
ContentThis comprehensive course covers some of the latest and most important research advances (over the last 3 years) underlying the creation of safe, trustworthy, and reliable AI (more information here: Link):

* Adversarial Attacks on Deep Learning (noise-based, geometry attacks, sound attacks, physical attacks, autonomous driving, out-of-distribution)
* Defenses against attacks
* Combining gradient-based optimization with logic for encoding background knowledge
* Complete Certification of deep neural networks via automated reasoning (e.g., via numerical relaxations, mixed-integer solvers).
* Probabilistic certification of deep neural networks
* Training deep neural networks to be provably robust via automated reasoning
* Fairness (different notions of fairness, certifiably fair representation learning)
* Federated Learning (introduction, security considerations)
Prerequisites / NoticeWhile not a formal requirement, the course assumes familiarity with basics of machine learning (especially linear algebra, gradient descent, and neural networks as well as basic probability theory). These topics are usually covered in “Intro to ML” classes at most institutions (e.g., “Introduction to Machine Learning” at ETH).

For solving assignments, some programming experience in Python is expected.