Seminar: Ausgewählte Themen des Machine Learning (BA and MA)
Organizer: Prof. Dr. Andreas Hotho, Dr. Anna Krause, Daniel Schlör
If you are interested in taking part in this seminar, please self-enroll into our WueCampus course. Further information about topics, meetings, etc will be made available via the WueCampus course. This seminar is open to BA and MA students.
Topics, Topic Assignment and Kickoff Meeting
This semester's course focuses Deep Learning algorithms for Anomaly Detection and Time Series Analysis.
Topics can be reserved before the kickoff meeting date. The topics will be announced on the WueCampus course some time before the kickoff meeting.
At the kickoff meeting, the topics - if not already assigned - will be distributed to the seminar participants present. Attendance is compulsory. Participants who have already reserved a topic but are absent without prior notice lose the right to their topic/place.
In this seminar, students will read their assigned scientific paper, find one related paper and write an elaboration on the main concepts of both papers. To this end, students will research related literature and review the main algorithm presented in the paper. The goals are:
- Write an elaboration which explains the given algorithm in a concise way. The elaboration must adhere to standards of scientific writing and use appropriate references.
- Give a presentation on the topic of the elaboration to other participants of the seminar.
Proof of performance
You must submit the following to the supervisor via email as separate PDFs:
- the slide set for the presentation
- a 6 - page LaTeX elaboration using the template provided by us excluding bibliography
Prior consultation with the supervisor is expressly advised.
The duration of the presentation is mandatory 20 minutes, after the presentation there will be a discussion in the seminar group (approx. 10 minutes). The presentation (incl. slides and abstract) will be graded with 40%, the paper with 30%. The last 30% evaluates the preparation, participation in the discussion group (especially with other presentations), independence of the elaboration and adherence to deadlines.
You can refer to the book
Markus Deininger and Horst Lichter and Jochen Ludewig and Kurt Schneider. Studien-Arbeiten: ein Leitfaden zur Vorbereitung, Durchführung und Betreuung von Studien-, Diplom- Abschluss- und Doktorarbeiten am Beispiel Informatik. 5th edition. vdf Hochschulverlag, Zurich, 2005.
as guideline for the preparation of a good seminar paper (incl. presentation and elaboration). It is available from the supervisor of the seminar (Prof. Dr. Andreas Hotho). We recommend the purchase of this book (9,50 €), because it can accompany you until the master thesis (and further). The grading of the seminar paper is done according to the scheme given there on page 77, adapted to the requirements of a seminar paper.
We aim to hold this seminar on site. Depending on the Covid-19 situation, the seminar may have to be moved online.
In case of online meetings, all meetings and lectures will be hosted via ZOOM. We ask that you have a working camera.
ZOOM requires a pre-installed client, which is available at https://zoom.us/download. However, an account is not required to participate. ZOOM is also available on Android and IOS.
(ZOOM also works in the browser. However, we cannot recommend this variant due to poorer performance).