Sort by
Refine Your Search
-
Listed
-
Category
-
Employer
- Forschungszentrum Jülich
- Technical University of Munich
- DAAD
- Carl von Ossietzky Universität Oldenburg
- Catholic University Eichstaett-Ingolstadt
- Fraunhofer-Gesellschaft
- Heidelberg University
- Helmholtz Zentrum Hereon
- Helmholtz-Zentrum Geesthacht
- Helmholtz-Zentrum Hereon
- Nature Careers
- Saarland University •
- Universität Siegen
- 3 more »
- « less
-
Field
-
the 01.02.2026 at the following conditions (PhD position): 50% = 19,92 hours Pay grade 13 TV-L limited 30.11.2028 Your tasks: Develop AI algorithms for real-time fault detection, fault classification
-
(ECLECTX team). This person occupying this position is planned to work on modeling computing elements, established and emerging, at different levels of abstraction, design and development simulation tools
-
of different faiths and beliefs. Grounded in the Christian view of human life, the KU aims to create an academic and educational culture of responsibility. The research group Reliable Machine Learning at the KU
-
using electromagnetic induction (EMI), and ground penetrating radar (GPR) will be combined with soil sensors systems and UAVs at different scales. In particular, we will combine borehole and surface GPR
-
sensors systems and UAVs at different scales. In particular, we will combine borehole and surface GPR as well as small-scale EMI measurements with root and shoot observations in controlled experiments
-
optimization to find the optimal set of parameters that improve process performance and material quality. Secondly, different machine learning strategies based on traditional supervised learning techniques (e.g
-
. It is not feasible to scan the full volume of such samples at the highest desired resolution. Therefore, we require an imaging scheme that acquires relevant features at different length scales and
-
EU MSCA doctoral (PhD) position in Materials Engineering with focus on computational optimization of
quality. Secondly, different machine learning strategies based on traditional supervised learning techniques (e. g. random forest (RF), artificial neural network (ANN)) will be applied using the parameters
-
exposed to Bayesian optimization to find the optimal set of parameters that improve process performance and material quality. Secondly, different machine learning strategies based on traditional supervised
-
of parameters that improve process performance and material quality. Secondly, different machine learning strategies based on traditional supervised learning techniques (e.g. random forest (RF