My research focuses on theoretical computer science and artificial intelligence, with a special focus on the following areas.

Computational learning theory. This field is concerned with the theoretical foundations of machine learning. I am particularly interested in how we can model and exploit special types of interaction with machines to make them learn using less data. This is not only a very interesting and challenging topic from a theoretical point of view, but it also has many potential applications.
Learning user preferences in web search, personalizing advertising in online markets, assisting clinicians in analyzing medical records, developing interactive robots - these and other problems require the use of machine learning, i.e., the design of algorithms that allow computers to learn based on data. Unfortunately, standard machine learning models and techniques are not suited to exploit the potential benefit that all these problem scenarios have in common, namely the interaction with a potentially co-operative partner. Current machine learning models assume that machines learn from random real-world data. My research team studies models in which machines learn from particularly well-chosen data, as though they were interacting with a co-operative "teacher".
In the tools and techniques we use, we mainly (but not exclusively) focus on discrete mathematics and algorithm analysis.

Formal language theory. My research group studies formal languages as objects of learning. In particular, we are interested in so-called pattern languages, relational pattern languages, and symbolic finite automata. Each of these formal language models is of interest to a different kind of application, and gives rise to fascinating research questions on the theoretical side.

Discrete structures in artificial intelligence. Aside from formal languages and automata, we also study the learnability of graphs in various settings, the learnability of combinatorial models of user preferences (such as conditional preference networks), and the learnability of boolean functions.


Theory of Machine Learning (Computational Learning Theory , theory of co-operative learning, theory of incremental learning, theory of query learning, sample efficiency)
Formal Language Theory (pattern languages, symbolic finite automata, and their learnability)
Algorithms (design and analysis of efficient algorithms)
Graph-Theoretic Aspects in Artificial Intelligence (learning graphs, conditional preference networks, search in graphs)
formerly also: Recursion Theory (inductive inference) and Heuristic Search


If you would like to work with me, please send me an email with your CV as well as with a brief description of your background and interests in mathematics and theoretical computer science.