Sort by
Refine Your Search
-
Listed
-
Category
-
Employer
- Technical University of Munich
- Leibniz
- Forschungszentrum Jülich
- Heidelberg University
- Nature Careers
- University of Tübingen
- ; Chemnitz University of Technology
- Fritz Haber Institute of the Max Planck Society, Berlin
- Helmholtz-Zentrum Geesthacht
- Max Planck Institute for Multidisciplinary Sciences, Göttingen
-
Field
-
external forcings on climate analysis of climate model output by means of classical statistical and machine-learning methods coordination of scientific workflows among project partners Your profile Master's
-
or Python Machine learning methods (for the baseline prediction for the reward funds) is beneficial We expect: Strong motivation to contribute to policy-relevant research Strong interest in teamwork and
-
to develop a 3D-generative algorithm for pharmaceutical drug design by using or combining novel machine learning approaches? How would you integrate machine learning, physics-based methods in an early-stage
-
-processing, and machine learning textual analysis of the full text of policy documents. Qualitative content thematic analysis is envisioned to compliment structural topic modelling to identify strategies and
-
theoretical methods and algorithms are required. The research project aims at deriving priors for Bayesian methods from atomistic simulations and machine learning. It also offers the opportunity to work with
-
Max Planck Institute for Multidisciplinary Sciences, Göttingen | Gottingen, Niedersachsen | Germany | 2 months ago
the structure from such data is challenging, and new theoretical methods and algorithms are required. The research project aims at deriving priors for Bayesian methods from atomistic simulations and machine
-
at least statistical insights into the risks and success rates of real, patient-specific aneurysms, their treatment options, and long-term prognosis. The project is complemented by contributions in machine
-
for data-efficient exploration and optimization within the process parameter space as well as for adaptive, data-driven machine learning to map the electrolysis process to a digital twin. Data workflows and
-
to generate reproducible, micrometer-scale controllable, and cost-efficient disease models by bringing together experts in molecular systems engineering, machine learning, biomedicine, and disease modeling
-
to generate reproducible, micrometer-scale controllable, and cost-efficient disease models by bringing together experts in molecular systems engineering, machine learning, biomedicine, and disease modeling