-
PhD Studentship: Robust, Certified, and Scalable Federated Machine Unlearning for Privacy-Preserving AI About the Project As federated learning systems become increasingly embedded in high‑stakes
-
and machine learning methodology to help deal with key challenges in developing such models in large-scale observational electronic healthcare record data. These models will be applied to important real
-
of dynamic radar scenes. The project combines methodological machine learning research with experiments on real automotive sensor data. You will have access to research vehicles and advanced radar prototypes
-
also include generative or predictive modeling of dynamic radar scenes. The project combines methodological machine learning research with experiments on real automotive sensor data. You will have access
-
will do Interpretable machine learning is a growing research area, with important applications in the biological sciences, such as understanding how different genes regulate each other within biological
-
. As a PhD researcher, you will unravel the atomic-scale mechanisms of hydrogen embrittlement in compositionally complex recycled steels, using density functional theory and machine-learned interatomic
-
central scientific challenge will be to learn integrated representations of forest ecosystems from datasets with very different characteristics, resolutions, coverage, and levels of supervision
-
predict interaction effects. Unlike robot-specific neural network models, the proposed approach aims to learn a universal representation of local interactions (fluid-structure, robot-robot, robot-object
-
, computational biology, statistics or a closely related field. You have strong programming skills, preferably in Python, and experience with machine learning or deep learning. Experience in computer vision
-
computational image analysis, computer vision and machine learning. The aim is to develop robust and standardized methods to link structural, mechanical and biological properties to biomaterial performance and