Sort by
Refine Your Search
-
position, you will lead the development of a probabilistic, error-aware surrogate model capable of delivering fast, uncertainty-quantified predictions for complex multiscale–multiphysics processes in OFPV
-
novel combinatorial, algebraic, and probabilistic tools, you will work on resolving fundamental extremal problems in the area of finite geometry. These problems have connections to Ramsey theory, coding
-
for approximate inference, probabilistic programming, Bayesian deep learning, causal inference, reinforcement learning, graph neural networks, and geometric deep learning. It comprises Jan-Willem van de Meent, who
-
, probabilistic programming, Bayesian deep learning, causal inference, reinforcement learning, graph neural networks, and geometric deep learning. It comprises Jan-Willem van de Meent, who serves as director, Max
-
the deployment of coordinated flexibility measures. The research topics to be addressed in the project are: How and to which extent can agent-based energy simulations, powered by AI-driven forecasts within a UDT
-
patterns and forecasting future energy scenarios for a specific region for hydrogen. These scenarios feed into the energy optimization models you develop and solve. The goal is to identify factors