My research is in the area of machine learning and artificial intelligence with interdisciplinary applications (in particular to music ♬♩) and a focus on cognitive modelling and complex temporal structures.

Machine Learning & Artificial Intelligence

  • Probabilistic Modelling: Bayesian inference, graphical models, artificial grammars, Monte-Carlo methods, approximate inference
  • Neuro-Symbolic Modelling: end-to-end differentiable parsing algorithms, deep neural networks, structured differentiable models
  • Structure Learning: feature discovery, structure learning in graphical models, parsing algorithms
  • Planning & Decision Making: reinforcement learning, classical planning, Monte-Carlo tree search, heuristic search, active learning

Cognitive Modelling

  • Music Cognition: perception of harmony & voice leading, hierarchical metrical structure, rhythm, expectation and surprise
  • Communication & Interaction: emergence of symbols in communication, cultural evolution, iterated learning paradigm


  • Music: music analysis & musical form, new interfaces for musical expression and education
  • Ethical AI: moral reasoning & autonomous systems
  • Medicine: 3D medical image analysis (CT/MRI) & semi-automatic segmentation
While I am particularly fascinated by human cognition, the involved questions are much broader, aiming at the comprehension of acting and learning systems in general and entailing a range of technical, philosophical, and practical challenges. All of my research projects are, in one way or another, related to one of the following high-level questions.

How do we perceive and represent the world?

(Perception and Learning)

When we perceive the world we learn something about it. However, perceiving the world does not mean to passively take in all information. For example, already on the level of our retina the visual input is preprocessed and transformed (things like edge detection happen here to some extent) such that what actually reaches our brain contains more relevant information. These transformations change how the external world is represented internally. And what makes a good representation depends on what the information should be used for. Perception is an active process in yet another way because our actions determine what we perceive and thus what we learn about the world. I can decide to open a box and learn what is inside or leave it closed and do something else instead. Learning and acting are thus intimately intertwined, which leads to the next question.

How do we take decisions?

(Acting and Planning)

Taking the right decisions is difficult mainly for two reasons. First, we do not have perfect knowledge of the consequences of our actions, either because the world is inherently non-deterministic or because we are lacking some information about it. For choosing the best action we thus have to take into account all of its possible outcomes. Second, our actions change the world, which means that they potentially have effects in the remote future including what the effect of future actions is. It is therefore not enough to only consider the very next action, but we effectively have to think about all possible sequences of actions and all of their possible outcomes – a task of overwhelming complexity. However, understanding the characteristics of our environment allows us to come up with acceptable solutions even in situations that otherwise seem intractable, as the intelligent behavior of many humans and animals proves.

How do we communicate with each other?

(Interaction and Communication)

Finally, our environment is populated with other agents that we interact with. These agents, too, are able to perceive, learn, act, plan, and communicate. Perceiving ourselves as one agent among many others is an integral part of our human self-conception. The resulting complex system of interacting agents has its own emergent dynamics and phenomena, including socially constructed narratives and cultural conventions.