Geometric Learning: Foundations and Applications
Abstract
Geometric Learning developed as a specific field of research that aims to learn from non-Euclidean domains, like graphs, manifolds, etc. In this course, we first introduce the basic theory and challenges related to learning from these data, presenting basic architectural solutions for graphs, point clouds, and meshes. Then, we present some applications that we developed for different domains, going from classification of relief patterns on 3D mesh surfaces, to the generation of 4D emotional faces, and talking heads.