PhD
Bavarian AI Chair for Mathematical Foundations of Artificial Intelligence at LMU
Akademiestr. 7
80799 München
Biosketch
Christopher began his PhD at the Bavarian AI Chair of Mathematical Foundations of Artificial Intelligence in early 2024 and soon after joined relAI. His research is dedicated to utilizing neural networks to learn and describe physical laws and systems.
Christopher holds a Bachelor’s degree in Industrial Engineering and a Master’s degree in Economathematics from Karlsruhe Institute of Technology. During his studies, he gained valuable experience as a research assistant, focusing on uncertainty quantification and the use of neural networks for weather system forecasting.
relAI Research
Uncertainty quantification for neural operators
Neural operators provide a powerful framework for applying machine learning to function spaces, making them well-suited for solving PDEs, inverse problems, and complex dynamical systems. Their ability to model intricate mappings has led to applications in fields such as meteorology or energy systems. However, their high-dimensional structure and infinite-dimensional function spaces pose challenges for uncertainty quantification, limiting their interpretability and reliability in critical applications. We develop new methodologies for probabilistic predictions and uncertainty quantification in complex and structured spaces, leading to improved decision-making under uncertainty, and advancing scientific machine learning in domains such as weather forecasting or quantum physics.