Block-Seminar "Hot Topics in Machine Learning"
The Hot Topics Seminar is an optional course in the module "Machine Learning - Theory and Applications" and is worth 3 LP (3 ECTS credits).
In the general case, it is not possible to take the Hot Topics Seminar as a standalone course. There are possible exceptions to this (e.g. it complements another ML or related course you are taking in parallel). In that case, a special request needs to be made.
Dates and Informations
Kickoff Meeting |
11.5.2020, 8 am, Link to virtual session NEW LINK: https://tu-berlin.zoom.us/j/97467160295?pwd=Y1pIU3piQVl1Q0xLb2xmcUtLb1FjZz09 |
Seminar Days |
14.7.2020, 9 am - 5 pm Room (or virtual room) will be announced soon |
Professor |
Prof. Dr. Klaus-Robert Müller |
Docent |
Dr. Marina Marie-Claire Höhne, marina.hoehne@tu-berlin.de |
Language |
Englisch |
ISIS |
This seminar takes a closer look at a mix of hot topics in machine learning including, but not limited to: deep learning, interpretable machine learning, optimal transport, reinforcement learning, machine learning in physics.
!!! Important !!! 0. There is no registration possible before the Kickoff Meeting (11.5.)!!!
1. The seminar is limited to 30 Students
2. If you take the ML2-X Module: This seminar is (an optional) part of the ML2-X Module and you can take the seminar. Alternative seminar options for the ML2-X Module are the big data seminar/data management seminar.
3. If you take the Cognitive Algorithm Module: This seminar is part of the Cognitive Algorithm Module and you can take the seminar.
4. If you don’t take the ML2-X Module or the Cognitive Algorithm Module: You have to check with your examination office if you can count the ECTS credits and get a written form. Note that the students attending the ML2-X Module and the Cognitive Algorithm Module have priority if there are too many participants.
This seminar takes a closer look at classical topics in machine learning. "Classical Topics in Machine Learning" is an optional course in the module "Machine Learning 2" and "Cognitive Algorithm" and is worth 3 LP (3 ECTS credits). There is no formal registration for the kick-off meeting. In the general case, it is not possible to take the seminar as a standalone course.
Students will read, understand, evaluate and present selected research papers on machine learning methods in different applications settings. At the end of the semester, each student will present his/her topic in a 20 min talk (+ questions) in English.