Improving Deep Learning by Inverse Square Root Linear Units (ISRLUs).

Brad Carlile Guy Delamarter Paul Kinney Akiko Marti Brian Whitney

Published in: CoRR (2017)

Keyphrases

square root
deep learning
floating point
kalman filtering
unsupervised learning
arrival rate
machine learning
probability density function
euclidean space
mental models
weakly supervised
steady state
multi class
object recognition
riemannian manifolds
face recognition
feature selection