Proximal Backpropagation

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size limitation of explicit gradient descent, which poses an impediment f...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Frerix, Thomas, Möllenhoff, Thomas, Moeller, Michael, Cremers, Daniel
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!