@@ -26,6 +26,10 @@ We are using these methods in different fields including modelling of the human
Recently, deep learning has been applied to non-structured 3D geometries as for example surface meshes and a new area of research named geometric deep learning has emerged. We have been using methods from geometric deep learning to analyse facial geometries, heart anatomies and are also developing methods for the analysis of the human inner ear system.
Recent work also includes methods for quantifying uncertainty in manifold-valued predictors, resulting in prbabilistic algorithms for both manifold learning and regression when the data at hand is known to satisfy nonlinear constraints or invariances encoded by a Riemannian manifold structure.
