IMPORTANT: ATML course will not be given in the academic year of 2021-2022. We invite you to check our new courses, Online and Reinforcement Learning and Probabilistic Machine Learning instead.
In fall 2019 Advanced Topics in Machine Learning (ATML) will be taught by Yevgeny Seldin and Christian Igel. In the course we will go in depth into a number of selected topics in machine learning, where we do our research. In particular, we plan to cover
PAC-Bayesian analysis (Chapters 2.4 + 2.5 + 3.8 + 3.9 in Yevgeny's lecture notes)
Online Learning (Chapter 5 in Yevgeny's lecture notes)
Reinforcement Learning
Deep Reinforcement Learning
The course is theoretically oriented and assumes that you have a strong mathematical background and like proving theorems about learning algorithms. We also do theory-driven applications. As a highlight, we list some master thesis projects done by the course graduates:
Niklas Thiemann, Christian Igel, Olivier Wintenberger, and Yevgeny Seldin. A strongly quasiconvex PAC-Bayesian bound. In Proceedings of the International Conference on Algorithmic Learning Theory (ALT), 2017.
Reinforcement Learning with Lego Mindstorms robots: https://www.youtube.com/watch?v=NUTv-oNWEYo.
We assume that you have taken the Machine Learning (ML) course taught by us. If you have a strong mathematical background and basic knowledge of machine learning it is possible to take ATML without taking ML. In this case, please, check taking ATML before/without ML and self-preparation instructions carefully. You should be able to solve the self-preparation assignment before joining the course, otherwise we strongly advise taking ML first. Be aware that our ML course is more theoretical than average machine learning courses and if you have taken a machine learning course elsewhere it does not necessarily prepare you for ATML. In particular, Introduction to Data Science (IDS) course given by DIKU is much lighter than ML and does not prepare you for ATML.
Lectures: The lectures will be held on Wednesdays 10:15-12:00 and 13:15-15:00. The first lecture of the course will be held on Monday, 13:15-15:00 in the first week of the course.
TA classes: We will have TA classes on Mondays 13:15-16:00 (except the first week of the course) and on Fridays 13:15-16:00. The students are free to come to either of the two classes or to both of them.