Why Do We Need Weight Decay in Modern Deep Learning?

Maksym Andriushchenko Francesco D'Angelo Aditya Varre Nicolas Flammarion

Published in: CoRR (2023)

Keyphrases

deep learning
unsupervised learning
unsupervised feature learning
machine learning
restricted boltzmann machine
deep architectures
mental models
weakly supervised
data sets
data mining
online learning