12 computer-algorithm "Integreat Norwegian Centre for Knowledge driven Machine Learning" Postgraduate positions at Forschungszentrum Jülich
-
Your Job: Energy systems engineering heavily relies on efficient numerical algorithms. In this HDS-LEE project, we will use machine learning (ML) along with data from previously solved problem
-
environments Design and implement reinforcement learning algorithms for control and manipulation, first in simulation and later on real experimental setups Refine a real-time planning and execution architecture
-
Bayesian computational statistics, differentiable programming, and high-performance computing, the project aims to deliver robust, interpretable, and scalable methods for metabolic flux analysis. You will
-
machine learning, deep learning, or AI. Solid mathematical, algorithmic, or physics background, distinct analytical skills. Very good programming (Python, C++) and computer (Linux, Windows) skills
-
Investigate instance and panoptic segmentation for endosymbionts and track them over time Implement, train and test novel machine-learning-based solutions on top-tier super-computing hardware Work in an
-
and Energy (HDS-LEE), the project offers an interdisciplinary research environment at the interface of bioengineering, computational biophysics, and data-driven modeling, with strong links to open
-
, earth sciences, energy systems, or material sciences University degree (M.Sc. or equivalent) in applied mathematics or in computational engineering science, computer science, simulation science with a
-
, energy systems, or material sciences A Masters degree with a strong academic background in mathematics, computer science, physics, material science, earth science, life science, engineering, or a related
-
. or equivalent) in applied mathematics or in computational engineering science, computer science, simulation science with a strong background in applied mathematics Excellent programming skills (Python, C/C
-
surrogates or approximators, such as random forests or shallow neural networks, trained to mimic the outputs of the original computations at a fraction of the cost. This hybridization aims not only