Extended Seminar – Systems and Machine Learning
The seminar will be jointly held by Profs. Carsten Binnig, Kristian Kersting, Mira Mezini and Andreas Koch.
Topics will include both ML for Systems as well as Systems for ML, e.g., using ML to improve database and software engineering systems but also papers leveraging novel hardware or other techniques to improve machine learning systems.
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.
Quick Links
Organization
Last offered | Current Winter Semester (20/21) |
Lecturer | Profs. Carsten Binnig, Kristian Kersting, Mira Mezini |
Assistants | Benjamin Hilprecht |
Examination | See Grading section below |
The kickoff meeting will be announced in Moodle (link above). |
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 software/hardware systems and machine learning is helpful. Participation is limited to 20 students.
For further questions feel free to send an email to dm@cs.tu-darmstadt.de. No prior registration is needed, however, please still send us an email so that we are able to estimate beforehand the number of participants, and have your E-mail address for possible announcements. Also make sure that you are registered in TUCaN.
Extended Seminar
What is “Extended” about this seminar? Students are expected to give a short talk that not only covers the assigned paper but also related work and relevant background. It is mandatory to discuss your presentation with us before the seminar.
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 and in addition write three reviews for other seminar papers to enable an in-depth discussion of each presented paper. We will provide review forms for this.
Because this is more work for students, students receive 4 CPs for Extended Seminars (instead of 3 CPs for regular seminars).
Grading
The slides, the presentation, the answers given to questions in your talk will influence the overall grade, as will the reviews and your moderation of the discussion. Furthermore, it is expected that students actively participate in the discussions, and this will also be part of the final grade.
To achieve a grade in the 1.x range, the talk and reviews need to exceed the recitation of the given material and include own ideas, own experience or even examples/demos. An exact recitation of the papers will lead to a grade in the 2.x range. A weak presentation and lack of engagement in the discussions may lead to a grade in the 3.x range, or worse. For the write-ups it is important that they provide a coherent view (like a survey paper), and do not simply consist of a concatenation of four paper summaries.
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.