This seminar is about machine learning and (data) systems. This year's topics will focus on ML for Systems i.e. using ML to improve data management systems.
Under the guidance of your supervisor you will
- use the given literature and search for additional literature to become acquainted with your topic
- write a survey paper, which includes analysis of related papers and background to the topic
- prepare and give a presentation about your topic and afterwards discuss the topic with the other participants
The work can be done either alone or in groups of up to 2 persons.
The topics will be assigned based on an on-line bidding process, which will be opened after the kick-off. The final assignment will be made a week later.
Organization
Last offered | Winter Semester (22/23) |
Lecturer | Profs. Carsten Binnig, Dr. Manisha Luthra |
Assistants | Johannes Wehrstein, M.Sc. |
Examination | See Grading section below |
The kickoff meeting will be at the 31th of October at 16:10-17:50 in room S202/C120 (Meeting in person). |
Course Infos
Below, you find some general information about the seminar. For all information regarding this year's seminar (including important dates) please check the moodle course linked above.
Prerequisites
It is not necessary to have prior knowledge in artificial intelligence, but prior knowledge in data systems and machine learning is helpful. Participation is limited to 20 students.
For further questions feel free to send an email to johannes.wehrstein@cs.tu-…. No prior registration is needed, however, please enroll in the Moodle course so that we are able to estimate beforehand the number of participants and can inform you about possible announcements. Also make sure that you are registered in TUCaN.
Extended Seminar
What is “Extended” about this seminar? Students are expected to write a detailed survey paper and give a short talk that not only covers the assigned paper but also related work and relevant background.
Survey Paper: It should be around 6 pages and should comprise a detailed survey on the topic including analysis of related papers and background to the topic. The paper must contain (i) an introduction describing the motivation and structure of the paper, (ii) a section on the methodology on how you classify and structure the related work, (iii) short summaries of the related work you analyzed, and a comparison based on the methodology introduced before, and (iv) conclusion summarizing the survey paper and pointing interesting open questions. This is just a guideline on what comprises a survey paper but does not reflect the actual structure of the paper. Further details will be announced in the Kick-off meeting and the workshops. Material to the topics and initial literature will be provided by your supervisor.
Presentation: The presentations will take in place in February / March 2023. After each talk there will be a discussion phase in which students are expected to participate actively. In particular, every student has to moderate one of these discussions. Date and Time will be announced.
Because this is more work for students, students receive 4 CPs for Extended Seminars (instead of 3 CPs for regular seminars).
Grading
The survey papers, the slides, the presentation and the answers given to questions in your talk will influence the overall grade. It is expected that students actively participate in the discussions, and this will also be part of the final grade. Furthermore, the supervisors grade your working style during the seminar and whether the delivered results meet the expectations and requirements of the supervisor. The detailed grading scheme is as follows (i) survey paper (40%), presentation and discussion (40%) and the supervisor’s grade of your work during the seminar (20%).
Schedule
See schedule on Moodle (link above)
Topics
All papers should be available on the internet or in the ULB. Note that Springer link often only works on campus networks (sometimes not even via VPN). If you cannot find a paper, contact us.
See moodle course for current topics.