From foundations of algorithmic information theory to asymptotically optimal yet infeasible methods showing the ultimate limits of machine learning, and all the way down to practically useful tricks for recurrent nets.

"We focus on learning agents interacting with an initially unknown world. Since the world is dynamic, unlike many other machine learning courses ours will put strong emphasis on learning to deal with sequential data."

The CoTeSys cluster of excellence investigates cognition for technical systems such as vehicles, robots, and factories.

"Is there an optimal way of learning non-reactive behaviors in general, unknown environments? Our recent theoretical insights affirm that the answer is yes."