Deep Network Regularization via Bayesian Inference of Synaptic Connectivity

Deep neural networks (DNNs) often require good regularizers to generalize well. Currently, state-of-the-art DNN regularization techniques consist in randomly dropping units and/or connections on each iteration of the training algorithm. Dropout and DropConnect are characteristic examples of such reg...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2018-03
Hauptverfasser:	Harris Partaourides, Chatzis, Sotirios P
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Bayesian analysis Iterative methods Neural networks Regularization Sparsity Statistical inference
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!