Sort by
Refine Your Search
-
identification of biological sounds using passive acoustic data. Passive acoustic monitoring will be conducted with species identification based on a neural network trained and tuned to the turbulent waters
-
Applications are sought for a fully-funded 42 month PhD studentship to work with Dr Rachel Nicks and Prof Stephen Coombes on the project: White Matter Computation: Utilising axonal delays to sculpt
-
on agentic approaches, where an LLM interacts with visual tools, which may themselves be neural networks. Central challenges include enabling LLMs to reason about visual structures, designing
-
are developed, modelled and controlled. You will create novel adaptative, physics-informed models that tightly integrate thermo-fluid dynamic laws, deep learning neural networks, and experimental data. A key
-
, you will leverage the power of graph neural networks – a novel ML architecture, capable of learning fundamental physical behaviour by modeling systems as graphs and encoding nonlinearities in these. As
-
/f/d, E13 TV-L, 50-75%) The position is limited for three years. Description of the project The research group of Prof. Dr. Frank Schreiber at the University of Tübingen deals with the physics
-
. - Neural networks and machine learning strategies for the analysis of scattering data. Large amount of scattering data obtained in our group requires development of the advanced analysis techniques. In
-
communications. Evaluation of model performance can be conducted based on the data collected through the water tank. We have the GPU machines ($14k) to develop deep neural networks for underwater communications
-
cooperation with Kopter Germany GmbH and the Engineering Risk Analysis Group of Prof. Straub, which provides information on both the health and the actual stress of helicopter components. For this so-called
-
architectures which leverage our increasing understanding of the behaviour of neural networks trained with DP to ameliorate these trade-offs in biomedical applications. - Foundations of private machine learning