My main research interests lie in the area of self-learning systems, which is part of the field of machine learning.
In particular, I do research on Gaussian processes. I look into how they can learn more efficiently, reducing both the data needed for learning and the computational time required.
I also combine Gaussian process techniques with other learning/identification techniques, like reinforcement learning, particle methods and system identication.
My Ph.D. thesis LQG and Gaussian process techniques - For wind turbine control is available here. It is mainly a collection of my papers.
If you are new to the machine learning technique called Gaussian process regression, I have also set up a student version of the thesis. It is meant to teach Gaussian process ideas to aspiring master students.
The source code behind the student version, through which all the plots were generated, is available on GitHub.
I've authored and co-authored several conference and journal publications. Here are the most important ones.