Sort by
Refine Your Search
-
the use of large language models to support neural network design and data preprocessing. The position involves close collaboration with experts in cardiovascular simulation and Scientific Machine Learning
-
particular, we aim to develop a neural network architecture that will allow us to accelerate solving AC power flow (AC-PF) computations, potentially facilitating real‑time contingency analysis, rapid design
-
-source software development and industrially relevant applications. Tasks include: Development of molecular descriptors from protein structures and simulations Design and training of QSPR and machine
-
network approaches for stress prediction in arterial walls and plaque. Another part of the project is exploring the use of large language models to support neural network design and data preprocessing
-
: Design hierarchical models that explicitly capture misspecifications in metabolic models Develop differentiable and scalable inference algorithms using automatic differentiation Implement HPC-tailored
-
modelling and the land-surface model used in the project. Develop simplified, fast-running model surrogates using machine-learning methods to replace very time-intensive simulations. Design an efficient
-
from protein structures and simulations Design and training of QSPR and machine learning models to predict ion-exchange isotherm parametersIntegration of predicted parameters into the CADET
-
Design and implement clustering and integration approaches (e.g., network-based and subspace clustering) Use co-regulation networks for gene function and protein–protein functional relationship prediction
-
manipulation in microfluidic environments Design and implement reinforcement learning algorithms for control and manipulation, first in simulation and later on real experimental setups Refine a real-time
-
to accelerate solving AC power flow (AC-PF) computations, potentially facilitating real‑time contingency analysis, rapid design‑space exploration, and on‑line operational optimization of power systems