Autonomous Learning: Summer School 2014

Program & Videos

Please note that there will be a printed program booklet available at our summer school.

All talks will be held in the Leibniz-Saal (E1 05),
Max Planck Institute for Mathematics in the Sciences (Leipzig, Inselstraße 22).

Monday, September 01, 2014
10:30 - 11:00Welcome address
11:00 - 12:30Theme 1: Learning representations
Shun-ichi Amari (RIKEN, Japan)
Information geometry and its applications to learning
12:30 - 14:30Lunch break
14:30 - 16:00Theme 1: Learning representations
Shun-ichi Amari (RIKEN, Japan)
Basic principles of supervised and unsupervised learning: toward understanding deep learning
17:30Get-together BBQ at Glashaus (on individual payment)
Tuesday, September 02, 2014
09:00 - 10:30Theme 3: Learning to act in real-world environments
Christos Dimitrakakis (Chalmers University of Technology, Sweden)
Planning under uncertainty: Markov decision processes
10:30 - 11:00Coffee break
11:00 - 12:30Theme 2: Acting to learn (exploration)
Keyan Ghazi-Zahedi (Max Planck Institute for Mathematics in the Sciences, Germany)
Intrinsically motivated exploration of behavioural modes
12:30 - 14:30Lunch break
14:30 - 16:00Theme 1: Learning representations
Thomas Martinetz (University of Lübeck, Germany)
Sparse coding and efficient sensing
16:00 - 16:30Coffee break
16:30 - 18:00Theme 2: Acting to learn (exploration)
Friedrich Sommer (Redwood Center for Theoretical Neuroscience, UC Berkeley, USA)
Information-theory based policies for learning in (embodied) closed sensori-motor loops
Wednesday, September 03, 2014
09:00 - 10:30Theme 3: Learning to act in real-world environments
Tamim Asfour (KIT Karlsruhe, Germany)
Structural bootstrapping for 24/7 humanoids
10:30 - 11:00Coffee break
11:00 - 12:30Theme 2: Acting to learn (exploration)
Marc Toussaint (Stuttgart University, Germany)
Bandits, global optimization, active learning, and Bayesian reinforcement learning -- understanding the common ground
12:30 - 14:30Lunch break
14:30 - 17:00Poster session
18:00Social event
Thursday, September 04, 2014
09:00 - 10:30Theme 3: Learning to act in real-world environments
Michael Beetz (Bremen University, Germany)
Autonomous Learning for Human-scale Everyday Manipulation Tasks
10:30 - 11:00Coffee break
11:00 - 12:30Theme 3: Learning to act in real-world environments
Helge Ritter (Bielefeld University, Germany)
Issues, algorithms, and challenges
12:30 - 14:30Lunch break
14:30 - 16:00Theme 1: Learning representations
Matthias Bethge (University of Tübingen, MPI for Biological Cybernetics, Bernstein Center for Computational Neuroscience, Germany)
Natural image statistics & neural representation learning
16:00 - 16:30Coffee break
16:30 - 18:00Concluding discussion

Date and Location

September 01 - 04, 2014
Max Planck Institute for Mathematics in the Sciences
Inselstraße 22
04103 Leipzig
Germany
see travel instructions

Scientific Organizers

Nihat Ay
MPI for Mathematics in the Sciences
Information Theory of Cognitive Systems Group
Leipzig (Germany)

Marc Toussaint
Stuttgart University
Coordinator of Priority Program Autonomous Learning (Germany)

Administrative Contact

Marion Lange
Stuttgart University / TU Berlin
Coordination Priority Program Autonomous Learning
Stuttgart (Germany)
Contact by Email

28.06.2018, 08:45