-
: This PhD project will develop model- and data-driven hybrid machine learning material models that capture the complex, nonlinear, path- and history-dependent behaviour of materials. The goal is to create
-
: This PhD project will develop model- and data-driven hybrid machine learning material models that capture the complex, nonlinear, path- and history-dependent behaviour of materials. The goal is to create
-
that activity-silent mechanisms, such as short-term synaptic plasticity, also play an important role. We will experimentally target these two mechanisms, using EEG in combination with machine learning to reveal
-
mechanics at the atomic scale. In this project, the University of Groningen will develop an array of state-of-the-art machine learning potentials for multi-component alloy systems that are relevant
-
described in the project overview. Owing to the current composition of the project team, there will be a mild preference for candidates opting for project 2 on “Models and machine learning”. An explanation
-
adaptation of state-of-the art machine learning codes to deal with redshift distortions, intrinsic (galaxy) biases, survey selection biases and in particular the complications encountered in photometric
-
for this position will have the following qualifications/qualities An MSc degree in chemistry or a related field. Very strong academic performance. Experience in molecular machine learning. Experience with