Re:Scientists See Promise in Deep-Learning Programs
by gdahl on Saturday November 24, 2012 @06:57PM
(#4826855)
That is not entirely accurate. The Science paper described how to (pre)train a deep belief net by training a sequence of RBMs. Contrastive divergence for RBM training (and more generally products of experts) was described in 2002 in "Training Products of Experts by Minimizing Contrastive Divergence" http://www.cs.toronto.edu/~hinton/absps/nccd.pdf
[ Parent
| on HN ]