-
We are seeking a highly motivated PhD student to perform fundamental research and to conceive truly sparse solutions (on both, CPU and GPU) for dynamic sparse training, aiming to cut the training costs and energy requirements of state-of-the-art deep learning models significantly, while...
-
. Finally, the research will develop efficient algorithms and test them on realistic networks and using real data from energy and public transport operators. The Doctoral student is also expected
-
-compliant data infrastructures that enable secure data sharing, reuse, and AI-driven analytics Exploring and implementing federated learning and privacy-preserving AI approaches for distributed clinical
-
feature spaces to find out-of-distribution atomic environments Use chemical neighborhood representations to detect sparse or unseen cases Combine ML features with chemical descriptors to enhance uncertainty
-
Extrapolation and Low-Reference Regimes Analyze MLFF feature spaces to find out-of-distribution atomic environments Use chemical neighborhood representations to detect sparse or unseen cases Combine ML features