CS-625 / 2 credits

Teacher: Brbic Maria

Language: English

Remark: Spring 2024


Every year


This seminar course covers principles and recent advancements in machine learning methods that have the ability to solve multiple tasks and generalize to new domains in which training and test distributions are different.



By the end of the course the student must be able to: Understand fundamentals and state-of-the-art transfer learning and meta-learning methods, learn to critically read research papers in the field, and utilize the learned concepts in their own research.


deep learning, transfer learning, meta-learning, few-shot learning, domain adaptation, domain generalization, self-supervised learning

Learning Prerequisites

Required courses


Assessment methods


In the programs

  • Number of places: 30
  • Exam form: Oral (session free)
  • Subject examined: Transfer learning and meta-learning
  • Lecture: 28 Hour(s)
  • Type: optional

Reference week

Related courses

Results from graphsearch.epfl.ch.