|M.Sc. David John|
Phone: +49 711 811-22400
Office address/Post address
Engineering Mathematics and Computing Lab (EMCL)
In December 2016 I finished my studies of technical mathematics at Karlsruhe Institute of Technology (KIT) with mechanical engineering and applied computer science as minor subjects.
In January 2017 I entered the PhD program of Robert Bosch GmbH and joined the Engineering Mathematics and Computing Lab (EMCL) directed by Prof. Dr. Vincent Heuveline as an external collaborator. My research topic is in the field of Uncertainty Quantification.
Uncertainty Quantification with focus on
- Inverse problems
- Bayesian inference
- Parameter identification
- Model inadequacy
- Uncertainty propagation
- Surrogate models
- Sensitivity Analysis
- D. John, V. Heuveline, M. Schober. GOODE: A Gaussian Off-the-shelf Ordinary Differential Equation Solver. Proceedings of the 36th International Conference on Machine Learning, PMLR 97:3152-3162, 2019. Matlab code: https://github.com/boschresearch/GOODE
- D. John, M. Schick, V. Heuveline. Learning model discrepancy of an electric motor with Bayesian inference. Preprint Series of the Engineering Mathematics and Computing Lab, Vol. 01, 2018. ISSN 2191-0693. DOI: https://doi.org/10.11588/emclpp.2018.1.51320.
- D. John, M. Schick, V. Heuveline. Bayesian inference for estimating model discrepancy of an electric motor. Proceedings in Applied Mathematics and Mechanics, Wiley Online Library, 2018. DOI: https://doi.org/10.1002/pamm.201800393.
Participations, conference contributions and talks
- Participation and Poster @ Modeling and Numerical Methods for Uncertainty Quantification (MNMUQ 2019), Summer School, Porquerolles Island, France, September 2-6, 2019. https://www.sigma-clermont.fr/en/mnmuq2019
- Participation in: Workshop - Uncertainty Quantification, Machine Learning & Bayesian Statistics in Scientific Computing, July 1-5, 2019, Heidelberg University. https://sites.google.com/view/match2019/overview
- Poster and spotlight talk @ 36th International Conference on Machine Learning, Long Beach, USA, 9.-15. June, 2019. https://icml.cc/
- D. John, M. Schick, V. Heuveline: Learning model discrepancy of an electric motor with Bayesian inference. 38th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, The Alan Turing Institute, British Library, London, UK, 2.-6. July 2018. https://max-ent.github.io/
- D. John, M. Schick, V. Heuveline: Bayesian inference for estimating model discrepancy of an electric drive model. SIAM Conference on Uncertainty Quantification (UQ18), Los Angeles, USA, 16.-19. April 2018. https://archive.siam.org/meetings/uq18/
- D. John, M. Schick, V. Heuveline: Bayesian inference for estimating model discrepancy of an electric drive model. 89th Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM), Munich, Germany, 19.-23. March 2018. https://jahrestagung.gamm-ev.de/
- Participation in: 4th GAMM Junior's and 1st GRK2075 Summer School 2017 Bayesian Inference: Probabilistic way of learning from data. Braunschweig, Germany, 10.-14. July 2017.
- Participation in: TUM-IAS Focal Period 2017 International Symposium: Machine Learning Challenges in Complex Multiscale Physical Systems. Munich, Germany, 9.-12. January 2017
- Uncertainty Quantification for hydraulic systems - with focus on the Smolyak sparse pseudo-spectral projection method - Master Thesis, Karlsruhe Institute for Technology (2016)
- Sparse grid collocation methods - Bachelor Thesis, Karlsruhe Institute for Technology (2013)
- GAMM Activity Group on Uncertainty Quantification (AGUQ)
- Heidelberg Chapter of SIAM
- Heidelberg Graduate School of Mathematical and Computational Methods for the Sciences (HGS MathComp)