-
‑space exploration, and on‑line operational optimization of power systems. Your tasks in detail: Become familiar with our previously developed neural network superstructure for learning iterative
-
instances to solve new, yet similar, instances more efficiently than with general purpose algorithms such as Netwon`s method. In particular, we aim to develop a neural network architecture that will allow us
-
prediction Integration of domain decomposition methods into the learning framework to enable efficient model parallel training Implementation and optimization of GPU-accelerated training pipelines Validation
-
efficient model parallel training Implementation and optimization of GPU-accelerated training pipelines Validation of models on patient-specific geometries obtained from MRI data Participation in conferences