|Time:||Wednesday, 12:30 - 2pm, first meeting: Nov. 4|
The seminar will be fully virtual/online and held on Zoom.
See ILIAS for Zoom link.
|Organizer:||Frank Hutter, Noor Awad, Fabio Ferreira|
|Web page:||ILIAS, HISinOne|
- we will meet every Wednesday, 12:30-2pm, starting Nov 4
- the seminar will be fully virtual and carried out with Zoom
- we will announce the Zoom meeting link on ILIAS
- link to ILIAS course
- link to HisInOne course
- list of papers released at end of the kick-off meeting
GeneralWelcome to the Automated Machine Learning Seminar webpage. The seminar language will be in English and it will be comprises of papers from three areas: learning to learn (L2L), hyperparameter optimization (HPO), and neural architecture search (NAS). We will start on Wednesday, Nov. 4 at 12:30-2pm on Zoom. Check out the ILIAS course (link above) for the Zoom link. The papers discussed in this seminar will be announced at the end of the kick-off meeting. We will assume all participants have understood the fundamental concepts presented in the AutoML course.
ProcedureWe will meet weekly to discuss research papers from a yet to be released list of papers. Every week, two students present each one paper and will lead the succeeding discussion. All other participants read the paper and submit 3 questions due the Monday before via ILIAS. The presenter will be given access to the questions before the presentation. The discussion after the presentation will be based but not limited to the submitted questions. During the discussion, all participants are asked to be involved as much as possible. We will discuss the paper, its merits, limitations, etc.. In the end, the participants are asked to provide constructive feedback to the presenter. The feedback will not be considered for grading. The final grade takes the oral presentation, the questions submitted and class participation into account. Besides the seminar topic, you will learn several skills necessary not only in academia:
- read and understand research papers
- assessing the strengths and weaknesses
- oral presentation in front of your peers
- discussion with your peers
- high level summary of research with which you are not intimately familiar.