Hard Mixtures of Experts for Large Scale Weakly Supervised Vision

Training convolutional networks (CNN's) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large CNN's that do not fit in the memory of a few GPU cards, or for parallelizing CNN trai...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2017-04
Hauptverfasser:	Gross, Sam, Ranzato, Marc'Aurelio, Szlam, Arthur
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Data points Decoding Experts Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!