Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines

Restricted Boltzmann Machines (RBM) continue to be a popular methodology to pre-train weights of Deep Belief Networks (DBNs). However, the RBM objective function cannot be maximized directly. Therefore, it is not clear what function to monitor when deciding to stop the training, leading to a challen...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Plahl, C., Sainath, T. N., Ramabhadran, B., Nahamoo, D.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Artificial neural networks Deep belief network Encoding Linear programming neural network feature extraction pre-training sparse representation Speech Speech recognition Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!