Deductive logic is the tool of choice when premises are or are not true. This seminar will focus on a generalization of logic when the aim is to maximize our expected utility in cases where a premise holds only with a certain probability.
In other words, we will study how to make optimal decisions under uncertainty. This relates to important problems in reinforcement learning, control theory and game theory.
Literature: David Barber, Bayesian Reasoning and Machine Learning
Modalities
On Tuesday, Oct 18th 2016, I will give general guidelines on "how to give a talk", and will outline the different topics. To choose a topic, you must be present on that occasion.
If you join, you will conduct a literature search on your topic, give a 45 min talk and summarize its contents in a report. You will receive 6 ECTS points and a grade based on: content of your talk (1/3), presentation (1/3) and quality of your report (1/3). This is a "Pflichtseminar" that is eligible towards the specialization in Computational Physics.
If you wish to participate, please send an email to lab manager Barbara Werner mailto:hamprecht-lab-manager@iwr.uni-heidelberg.de?subject=Advanced-ML-S.... First come, first serve. If you have previously sent me an email, please forward your original message to the above address.
Venue
Tuesdays at 14:00, in the large seminar room, 3rd floor of HCI: Berliner Strasse 43.