On the importance of normalisation layers in deep learning with piecewise linear activation units.

Zhibin Liao Gustavo Carneiro

Published in: WACV (2016)

Keyphrases

piecewise linear
deep learning
deep belief networks
unsupervised learning
unsupervised feature learning
dynamic programming
machine learning
restricted boltzmann machine
chaotic map
mental models
weakly supervised
data analysis
hyperplane
information retrieval
feature space
named entities