I am the group leader of the Amsterdam Machine Learning Lab (AMLab). My research interests focus on development of computationally scalable and data-efficient methods for generative AI, with applications to a wide range of domains, including healthcare, neuroscience, robotics, and the modeling of physical systems. Much of my work builds on ideas from probabilistic machine learning and Bayesian statistics; I am probably best known for my contributions to probabilistic programming research. 

Roles in Hybrid Intelligence: Participant

Hybrid Intelligence Research Lines: Adaptive HI, Collaborative HI, Explainable HI 

Hybrid Intelligence Project(s): 

• 2.9: Bayesian Multi-agent Reinforcement Learning for Learning to Collaborate with Humans
• 3.17: Causal Representations for Open-Ended, Lifelong Hybrid Intelligence

Research interests: Generative AI, Probabilistic Programming, Differentiable Programming, AI for Scientific Computation, Planning as Inference, World Models, Theory-of-Mind Inference.

Affiliations:

• Amsterdam Machine Learning Lab (AMLab), University of Amsterdam

Other information: AMLab page