• Machine learning
• Image processing
• Statistical modelling
Wouter is a researcher in artificial intelligence and statistics. He obtained a Master of Science degree in Neuroscience from Maastricht University in 2013, with a focus on how the brain processes information. For his master thesis he interned at the Werner Reichardt Centre for Integrative Neuroscience in Tübingen, Germany. During his time there he worked on developing a computational model of how animal brains guide eye movements, such that they gather as much information as fast as possible.
In 2013, he started his PhD in Artificial Intelligence at Delft University of Technology, where he worked on systems that learn to make decisions. In particular, he focused on domain adaptation in machine learning, which is concerned with data from different populations. The aim is to learn from one population and generalize specifically to a target population. His research output consists of theoretical conditions for targeted generalization, domain-adaptive classification algorithms, robust parameter estimators and analyses of sampling variance. In 2016, he visited Cornell University in the U.S. to work on the combination of domain adaptation and causal inference.
Wouter is generally interested in mathematical models of intelligent behavior, probabilistic graphical models, statistical inference and probability theory.