In this topic we will advance the fundamental mathematical understanding of artificial neural networks, e.g., through the design and rigorous analysis of stochastic gradient descent methods for their training. Combining data-driven machine learning approaches with model order reduction methods, we will develop fully certified multi-fidelity modelling frameworks for parameterised PDEs, design and study higher-order deep learning-based approximation schemes for parametric SPDEs and construct cost-optimal multi-fidelity surrogate methods for PDE-constrained optimisation and inverse problems.
| Böhm, Christoph | Professur für Theoretische Mathematik (Prof. Böhm) |
| Dereich, Steffen | Professorship for Theory of Probability (Prof. Dereich) |
| Engwer, Christian | Professorship for Applications of Partial Differential Equations |
| Jentzen, Arnulf | Professorship for applied mathematics (Prof. Jentzen) |
| Kuckuck, Benno | Professorship for applied mathematics (Prof. Jentzen) |
| Ohlberger, Mario | Professorship of Applied Mathematics, especially Numerics (Prof. Ohlberger) |
| Rave, Stephan | Professorship of Applied Mathematics, especially Numerics (Prof. Ohlberger) |
| Weber, Hendrik | Professorship of Mathematics (Prof. Weber) |
| Wirth, Benedikt | Professorship of Biomedical Computing/Modelling (Prof. Wirth) |
| Böhm, Christoph | Professur für Theoretische Mathematik (Prof. Böhm) |
| Dereich, Steffen | Professorship for Theory of Probability (Prof. Dereich) |
| Engwer, Christian | Center for Nonlinear Science |
| Jentzen, Arnulf | Professorship for applied mathematics (Prof. Jentzen) |
| Kuckuck, Benno | Professorship for applied mathematics (Prof. Jentzen) |
| Ohlberger, Mario | Professorship of Applied Mathematics, especially Numerics (Prof. Ohlberger) |
| Rave, Stephan | Professorship of Applied Mathematics, especially Numerics (Prof. Ohlberger) |
| Weber, Hendrik | Professorship of Mathematics (Prof. Weber) |
| Wirth, Benedikt | Professorship of Biomedical Computing/Modelling (Prof. Wirth) |
