Hauptseminar Machine Learning (WS 15/16)


Please be aware that the Vorbesprechung/first session for the “WS1516 Hauptseminar: Machine Learning” is planned for the 2nd week of the winter term *** Oct 22nd 09:45 – 11:15 in room 0.457 ***.

Please note that your participation at the Vorbesprechung/first meeting is mandatory (unless you deregister) – if you are unavailable, please contact Prof. Toussaint in time before the date.

Also, please note that as mentioned in the text of the Hauptseminar announcement, background in Machine Learning is necessary.

In this course of seminar lectures, we build upon previous knowledge of machine learning to dwell on more advanced topics. Students are assumed to have a background in Machine Learning. The easiest way to achieve this is to have followed our own Introduction to Machine Learning course, but having followed lectures at other institutes or in MOOC is also considered a valid substitute (although verification may be required).

The seminars will be held by the students, for the students. The students will be divided into groups of 2, each of which will work, during the course of the semester, on a specific problem, for which they will have to develop and compare multiple solutions based on standard and advanced machine learning models. During the regular bi-weekly meetings, each group presents to the rest of the class their own progress.

This year’s projects are:
* Learning Robot Dynamics
* Discrete Synthesisation of Text and Music
* Go Game Winner Classifier