263-5155-00L  Causal Representation Learning

SemesterAutumn Semester 2020
LecturersB. Schölkopf
Periodicitynon-recurring course
Language of instructionEnglish
CommentThe 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.


AbstractDeep neural networks have achieved impressive success on prediction tasks in a supervised learning setting, provided sufficient labelled data is available. However, current AI systems lack a versatile understanding of the world around us, as shown in a limited ability to transfer and generalize between tasks.
ObjectiveThe goal of this class is for students to gain experience with advanced research at the intersection of causal inference and deep learning.
ContentThe course focuses on challenges and opportunities between deep learning and causal inference, and highlights work that attempts to develop statistical representation learning towards interventional/causal world models. The course will include guest lectures from renowned scientist both from academia as well as top industrial research labs.

Deep Representation Learning, Causal Structure Learning, Disentangled Representations, Independent Mechanisms, Causal Inference, World Models and Interactive Learning.
Prerequisites / NoticeBSc in Computer Science or related field (e.g. Mathematics, Physics) and passed at least one learning course e.g. Intro to Machine Learning or Probabilistic Artificial Intelligence.