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.


263-5155-00 SCausal Representation Learning
The lecturers will communicate the exact lesson times of ONLINE courses.
2 hrs
Tue16:00-18:00ON LI NE »
B. Schölkopf

Catalogue data

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.

Performance assessment

Performance assessment information (valid until the course unit is held again)
Performance assessment as a semester course
ECTS credits2 credits
ExaminersB. Schölkopf
Typeungraded semester performance
Language of examinationEnglish
RepetitionRepetition only possible after re-enrolling for the course unit.

Learning materials

Main linkInformation
Only public learning materials are listed.


No information on groups available.


PriorityRegistration for the course unit is only possible for the primary target group
Primary target groupData Science MSc (261000)
Computer Science MSc (263000)
CAS ETH in Computer Science (269000)

Offered in

CAS in Computer ScienceSeminarsWInformation
Data Science MasterSeminarWInformation
Computer Science MasterSeminarWInformation
Computer Science MasterSeminar in General StudiesWInformation