Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Field
-
. Implement and optimize data representations and pipelines suitable for machine learning and uncertainty quantification. Collaborate with AI/ML experts to design and test inference methods that map
-
). This position focuses on the machine learning methodology of the project, aiming to: Develop probabilistic spatio-temporal models that integrate uncertainty from climate projections into land-use forecasts
-
of scalable uncertainty quantification (UQ) methods is a particular emphasis to support the integrated simulation goals of the MAC. A PhD and research experience in one of these areas is required. This position
-
greatest challenges. With a history of novel research in computational modeling, optimization, and uncertainty quantification in physics-based and data-based simulation, CaSE faculty enable engineers
-
projects in computer vision, multi-modal ML, digital twins or biomedical ML. Familiarity with uncertainty quantification and model explainability methods. Strong software engineering practices: Git
-
Development of robust design methods Uncertainty quantification and management in structural design Processing optimisation and thermal analysis of polymers Non-destructive testing Experimental characterisation
-
simulations and multiscale spatial-omics data. • Integrate uncertainty quantification into scientific machine learning workflows and optimize the design of computational (ABM) and wet-lab experiments
-
mathematical modelling, with a focus on real-world applications. This includes statistics, uncertainty quantification, data analysis, signal processing, (mathematical foundations of) machine learning, and
-
human and natural systems as well as intrinsic variability. The need to translate to variables and scales relevant for stakeholders with appropriate uncertainty quantification requires physics-guided AI
-
Networks for cosmology, neutrino and/or collider physics, 2) Domain adaptation methods / model robustness, 3) Uncertainty quantification, 4) Model interpretability. Experience with other deep learning