7.4k citations · 24.2k across the 136 of their papers we have counts for
Showing 2014Show all
2 papers · 1 filter
cs.LG2014
Deep Tempering
Guillaume Desjardins, Heng Luo, Aaron Courville +1
Restricted Boltzmann Machines (RBMs) are one of the fundamental building blocks of deep learning. Approximate maximum likelihood training of RBMs typically necessitates sampling fr…
stat.ML2014★ 62 cited
An empirical analysis of dropout in piecewise linear networks
David Warde-Farley, Ian J. Goodfellow, Aaron Courville +1
The recently introduced dropout training criterion for neural networks has been the subject of much attention due to its simplicity and remarkable effectiveness as a regularizer, a…