Person
Katharina Ensinger
M. Sc.Doctoral Researcher (external)
Address
Since June 2020 I am a Ph.D. student, supervised by Prof. Dr. Sebastian Trimpe at the Institute for Data Science in Mechanical Engineering in collaboration with the Bosch Center for Artificial Intelligence in Renningen. I am in particular interested in dynamics model learning and combining data driven models with structural information. Currently I am trying to leverage numerical methods for learning tasks in order to benefit from both approaches. Numerical methods are able to respect mathematical and physical properties of the underlying dynamical system and produce interpretable simulations. Part of these properties can be incorporated into the learning task if the dynamical system is unknown. Before joining the two groups I obtained my Master’s degree in mathematics from the
University of Stuttgart in 2019. In my master’s thesis I dealt with deep neural networks to solve partial differential equations.
Publications
| Source | Author(s) |
|---|---|
| [Contribution to a book, Contribution to a conference proceedings] Structure-Preserving Gaussian Process Dynamics Machine learning and knowledge discovery in databases : European Conference, ECML PKDD 2022, Grenoble, France, September 19-23, 2022 : proceedings / Massih-Reza Amini, Stéphane Canu, Asja Fischer, Tias Guns, Petra Kralj Novak, Grigorios Tsoumakas, editors. - Part 5, 140-156, 2023 [DOI: 10.1007/978-3-031-26419-1_9] | Ensinger, Katharina (Corresponding author) Solowjow, Friedrich Ziesche, Sebastian Tiemann, Michael Trimpe, Johann Sebastian |
| [Preprint] Structure-preserving Gaussian Process Dynamics, 2022 [DOI: 10.48550/arXiv.2102.01606] | Ensinger, Katharina Solowjow, Friedrich Ziesche, Sebastian Tiemann, Michael Trimpe, Johann Sebastian |