Semantic Deep Learning

Scope:

This seminar is concerned with selected methods and systems of semantic deep learning. Research on semantic deep learning mainly focuses on the task-oriented combination of deep learning with symbolic knowledge representation and reasoning in general, and semantic web technologies in particular. In addition, the rationalization and semantic explanation of deep learning models and results to the human user is of interest (explainable AI). In this seminar, we will take a closer look at advanced methods, systems and tools for semantic deep learning, and discuss their strengths and weaknesses.

The seminar type is classic in the sense that registered participants will present the assigned topics, and discuss the strength and weaknesses of presented approaches. In addition, there will be two dedicated opponents for each presentation of an assigned topic. Successful participation in the seminar will be graded; please check the requirements page in this regard.

The seminar counts 7 ECTS credit points.

Prerequisites:

This seminar aims primarily at advanced master students in Computer Science who preferably hold a B.Sc. degree in this or related field. Good knowledge in AI, in particular not only in deep learning but also basics of symbolic knowledge representation and reasoning / semantic Web is required. Selected background references are given on the topic page and expected to be read and utilized by registered participants as appropriate. Attendance of the seminar without registration (no presentation and certificate) by anyone who is interested in the topics is, of course, very much welcome but subject to available space. The seminar language is English or German depending on the audience.

Date and Location:

The seminar is held weekly on Thursday from 4pm (16:00) to 6pm at DFKI in room “Turing 1” (NB R +2.30). The location can be accessed via the entrance of the DFKI main building D3.2. You may ask at the reception in the lobby of the building for further directions. Please check the seminar schedule frequently for changes.

Registration and Topic Assignment:

Full registration to the seminar requires a pre-registration which is confirmed by the seminar leader. For your pre-registration request, please send the following and complete (1-6) information to klusch@dfki.de:

1. Full name (first name and surname)
2. Enrollment number (Matrikulationsnummer
3. Contact details (email, phone, mail address)
4. Course of studies (e.g. CS) and number of current semester (incl. SS 2019)
5. List of attended courses and seminars with grades (otherwise indicate when grade will be available)
6. Preferred and available topic (or ordered list of topics) for its presentation by you at the seminar.

It is recommended to carefully check the topic reference papers and preliminary dates of topic presentations (see schedule) BEFORE sending a pre-registration request. Reference papers are available in the web or can be provided on request. Please also note that incomplete pre-registration requests will not be considered.

Pre-registration with assignment of topics will be decided until April 12, 2019 EOB latest

• during introduction meeting on February 6, 2019
• on request per pre-registration E-Mail
• during the first (welcome) session of the seminar on April 11, 2019

A notification about your pre-registration request and topic assignment will be sent to you by the seminar leader.

NOTE:

In case of confirmed pre-registration your full registration in HISPOS until May 6, 2019 latest is mandatory for full registration to the seminar. Please note that the official 3-weeks-rejection period according to the examination regulation for seminars counts from the date of the topic assignment (i.e. the date of pre-registration confirmation e-mail sent to you by the seminar leader).

Pre-registration requests after pre-registration deadline might be considered if the official 3-weeks-rejection period is not being claimed by the requester but decision made until the deadline for full registration (May 6).

Registration without confirmed pre-registration is not valid and will not be accepted by the examination office.