Sort by
Refine Your Search
-
the use of hierarchical graph neural networks for modeling multi-scale urban energy systems. By combining advances in Physics-Informed Machine Learning (PIML) and Graph Neural Networks (GNNs) with real
-
the use of hierarchical graph neural networks for modeling multi-scale urban energy systems. By combining advances in Physics-Informed Machine Learning (PIML) and Graph Neural Networks (GNNs) with real
-
foundations. Candidates should possess an exceptional academic record and a strong mathematical background. Experience conducting large-scale computational experiments (e.g., multi-GPU systems) is advantageous
-
optimization – with rigorous theoretical analysis. The ideal candidate has strong machine learning and AI expertise and is comfortable with – or eager to learn – large-scale multi-GPU experimentation
-
secondments at UCL – University College London and at University of Leeds (UK). We are looking for you! Do you want to be trained to develop multi-level thrombosis risk prediction models by integrating insights
-
are looking for you! Do you want to be trained to develop multi-level thrombosis risk prediction models by integrating insights from cell-, thrombus-, and organ-level perspectives? While being part of a
-
. Empa is a research institution of the ETH Domain. Empa's Laboratory of Biomimetic Membranes and Textiles is a pioneer in physics-based modeling at multiple scales. We bridge the virtual to the real world
-
topological cell guidance cues and multi-scale directional porosity. The laboratory is embedded in ETH Zurich’s Department of Health Sciences & Technology (D-HEST). D-HEST is a stimulating environment for
-
CoSi project (Co-Evolution and Coordinated Simulation of the Swiss Energy System and Swiss Society), we are seeking a motivated and qualified PhD candidate to develop neighbourhood- and district-scale