Seminar an der Universitšt des Saarlandes, Fachrichtung Informatik, LVst 109686
This seminar is concerned with selected methods and applications of deep learning in different industries. Deep learning is a subfield of Machine Learning, which, in turn, is one core area of Artificial Intelligence. The interest in deep learning exploded in the past decade. In the early 2000s, the exponential growth of available computational power and training data enabled major breakthroughs in the application of nature-inspired computing with (deep) artificial neural networks that were not possible prior to this. In addition, research on hybrid or semantic deep learning recently started to investigate the potential of deep learning combined with symbolic knowledge representation and semantic reasoning. We will take a closer look at deep learning methods and their applications in finances, healthcare, autonomous driving and recommendation.
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. There will be two dedicated opponents for each presentation of an assigned topic. All certificates for successful participation in the seminar will be marked; please check the requirements page in this regard.
The seminar counts 7 ECTS credit points.
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 Artificial Intelligence and deep learning is required. Selected references on deep learning in general and its application in selected industries in particular are given on the topic page and expected to be read and utilized by registered participants in due course of their preparation for the seminar. 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.
Seminar Date and Location:
The seminar is held weekly on Monday from 2pm (14:00) to 4pm at DFKI in room “Turing 1” (NB R +2.30).
The only exceptions are the first (welcome) session, which will be held on Monday 9.4.2018 from 4pm (16:00) to 6pm, at DFKI in room “Reuse” (MB R -2.17), and the regular session on 14.5.2018, which also will be held in room “Reuse” (MB R -2.17).
The locations 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:
Registration for the seminar is closed; topic assignment completed
Full registration to the seminar in HISPOS requires a pre-registration confirmed by the seminar leader. For your pre-registration request, please send the following complete (1-6) information to email@example.com:
It is strongly recommended to CAREFULLY READ and REFLECT on the content of indicated REFERENCE PAPER(S) with respect to your scientific background, time and skills BEFORE APPLYING for presenting the respective topic(s) at the seminar.
Please note that incomplete registration requests will not be considered.
Pre-registration with assignment of topics will be done until April 10, 2018 EOB latest:
A notification about your pre-registration request and topic assignment will be sent to you by the seminar leader.
In case of confirmed pre-registration your registration in HISPOS until May 2, 2018 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). Registration to the seminar in HISPOS without confirmed pre-registration is not valid and will not be accepted by the examination office