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...

Full description

Bibliographic Details

Published in:	Conference record - Asilomar Conference on Signals, Systems, & Computers pp. 864 - 868
Main Authors:	Douglas, Scott C., Yu, Jiutian
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2018
Subjects:	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 Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!