Sort by
Refine Your Search
-
Listed
-
Category
-
Program
-
Employer
- Fraunhofer-Gesellschaft
- Technical University of Munich
- Forschungszentrum Jülich
- Nature Careers
- DAAD
- Leibniz
- ;
- Free University of Berlin
- Deutsches Elektronen-Synchrotron DESY •
- Helmholtz-Zentrum Geesthacht
- Max Planck Institute for Molecular Genetics •
- Max Planck Institutes
- Technische Universität München
- University of Bremen •
- University of Tübingen
- 5 more »
- « less
-
Field
-
you will do Time series forecasting problems with Neural Differential Equations on Graphs Solve PDEs with Physics Informed Neural Networks and train Diffusion Models Develop and test new deep learning
-
you will do Driving innovative AI research through the development and implementation, practical application, theoretical analysis and evaluation of AI algorithms Use of XAI tools to explain machine
-
strategies. Your tasks in detail: Enhance existing Bayesian state estimation with reliability margins using both simulated and, if necessary, real-world grid data. Develop Use-Case-Specific Reinforcement
-
, but also in traffic monitoring or in the media context, for example when it comes to automatic metadata extraction and audio manipulation detection. Another focus is the development of algorithms
-
and simulation aspects across a wide range of fields - from biomechanics and geophysics to polymer-fluid coupling. Further areas of interest include numerical algorithms for high-dimensional problems
-
, but also in traffic monitoring or in the media context, for example when it comes to automatic metadata extraction and audio manipulation detection. Another focus is the development of algorithms
-
-omics data sets generated with innovative high-throughput technologies used in Research Sections I and II (e.g. sensory, metabolome, proteome and transcriptome data) by using efficient algorithms and
-
and evaluation of innovative data- and machine learning-based systems to integrate more renewable energy into our energy systems and make energy use more efficient. We develop new optimization methods
-
to co-design algorithms and circuits to develop efficient neuromorphic hardware, tailored to target tasks. In detail, you will: develop circuit-plausible training/inference algorithms and analyze in
-
promising alternative to classic methods of process optimization due to its adaptive decision making and data efficiency. In this thesis, a BO algorithm for the optimization of laser processes is to be