Preprint
Universal Approximation Theorems for Differentiable Geometric Deep Learning
Abstract
This paper addresses the growing need to process non-Euclidean data, by
introducing a geometric deep learning (GDL) framework for building universal
Authors
Kratsios A; Papon L
Publication date
January 13, 2021
DOI
10.48550/arxiv.2101.05390
Preprint server
arXiv