Analysis of (sub-)Riemannian PDE-G-CNNs

Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced f...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Bellaard, Gijs, Bon, Daan L. J, Pai, Gautam, Smets, Bart M. N, Duits, Remco
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Mathematics - Differential Geometry
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!