Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- NTNU - Norwegian University of Science and Technology
- Delft University of Technology (TU Delft)
- NTNU Norwegian University of Science and Technology
- Amsterdam UMC
- CNRS
- Centrum Wiskunde en Informatica (CWI)
- Eindhoven University of Technology (TU/e)
- SciLifeLab
- University of Oslo
- Uppsala universitet
- Wageningen University & Research
- BRGM
- Chalmers University of Technology
- Constructor Knowledge Labs gGmbH
- Fondazione Bruno Kessler
- Forschungszentrum Jülich
- Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt
- Helmholtz-Zentrum Dresden-Rossendorf •
- Imperial College London
- Inria, the French national research institute for the digital sciences
- Monash University
- Norwegian University of Life Sciences (NMBU)
- REQUIMTE - Rede de Quimica e Tecnologia
- Technical University of Munich
- The University of Manchester
- UNIVERSITAT POMPEU FABRA
- University of Birmingham
- University of Exeter
- University of Warwick;
- 19 more »
- « less
-
Field
-
methods that incorporate domain-specific information into latent-variable models. Investigate methodological questions related to computation, identifiability, uncertainty quantification, and interpretation
-
discovery and inference, with an emphasis on robustness, scalability, uncertainty quantification, expert knowledge integration, and multi-scale causal abstraction and representation learning. Your Job How are
-
design spaces, long-duration simulations, and real-time applications. This PhD project will develop physics-informed deep learning and surrogate modelling approaches to accelerate simulation, uncertainty
-
Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt | Stein bei N rnberg, Bayern | Germany | about 1 month ago
, how it can be extracted, and how confidently conclusions can be drawn. Develop and apply approaches for uncertainty quantification, robust inference, and validation of biomedical imaging results. Work
-
generation and pressure evolution. Our approach will combine physical insight with data-driven techniques and uncertainty quantification, offering fast, reliable predictions and contributing to safer, longer
-
is decentralized or only partially observable? Depending on the research direction, you may employ techniques from mathematical modelling, machine learning, uncertainty quantification, distributed
-
causal inference, integration of heterogeneous data sources, uncertainty quantification Work with a wide range of data types, for example dietary records, biomarkers, omics data, registry data, and sensor
-
-driven model selection, and deep learning for data analysis and feature extraction from characterisation data. Surrogate modelling will be employed to reduce computational costs, and AI-based uncertainty
-
statistical learning theory and probabilistic models; prior exposure to notions of robustness, resilience, or uncertainty quantification is an advantage. Mathematical maturity and experience with formal
-
Computational Fluid Dynamics (CFD) has become indispensable for aerospace design, many important problems—including high-fidelity flow simulations, uncertainty quantification, and multidisciplinary optimization