Aktuelles

Abstract: Accurate modeling of physical systems is of great importance to engineers. In this thesis, we construct novel machine learning models based on the Neural ODE approach in Chen et al. (2018) and compare them to existing architectures. The evaluation is performed on multiple physical systems,…

More details here Github repository here

More details here

at the Seminar on Numerical Analysis and Applied Mathematics at KU Leuven

News

Tim Beyer presents his B.Sc. thesis on "Neural Ordinary Differential Equations for Physical Problems"

Zhiyi He presents her Semester Thesis on "Magnetic Resonance Images Reconstruction Using Generative Adversarial Networks and Uncertainty Analysis" on 08.05.2020

Martin Kronthaler presents his Semester Thesis on "Physics Enhanced Neural Networks for the Prediction of Dynamical Systems" on 24.01.2020

New work on "Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems"

Tobias Pielok presents his Semester Thesis on "Bayesian Coarse-Graining with Memory" on November 22nd

Andreas Felderer presents his B.Sc. thesis on "Machine Learning Tools for the Solution of High Dimensional Problems in Random Media"

New work on "A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime"

Our group will participate in this year's SIAM CSE 2019 conference with 5 papers

New work on "Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data"

Talk on "Data-driven, physics-aware, coarse-grained models"