The AI4Science Group (head: Frank Noé) is an interdisciplinary research unit active in the development of machine learning methods for the physical sciences. We have a strong profile in computational statistics, simulation and learning algorithms, and scientific software development. As a closely collaborating team of mathematicians, chemists, physicists and computer scientists, we put great emphasis on bridging the gaps between the various disciplines.

Our main research areas are

• Physics-constrained learning algorithms
• Complex dynamical systems analysis
• Efficient generative learning methods for statistical mechanics
• Highly accurate machine learning methods for quantum mechanics
• Inference and enhancement of cutting-edge microscopy method