Gradual training of deep denoising auto encoders

Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2014-12
Hauptverfasser:	Kalmanovich, Alexander, Chechik, Gal
Format:	Artikel
Sprache:	eng
Schlagworte:	Coders Datasets Noise reduction Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!