Why RELU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks

Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures sometimes results in "dying ReLU units" with near-zero outputs. We first explore this condition via simulation using the CIFAR-10 da...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Conference record - Asilomar Conference on Signals, Systems, & Computers S. 864 - 868
Hauptverfasser:	Douglas, Scott C., Yu, Jiutian
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.10.2018
Schlagworte:	adaptation models adaptive algorithms algorithm design and analysis Analytical models backpropagation algorithms Computer architecture Convergence Machine learning Neural networks Probability Training
ISSN:	2576-2303
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!