2006, in 2 pieces
2 records · 0 notes
December 1
Yoshua Bengio et al.
Greedy Layer-Wise Training of Deep Networks
Showed experimentally that layer-wise unsupervised pretraining eases the difficulty of training
Year only 1
Geoffrey Hinton, Simon Osindero, Yee-Whye Teh
A Fast Learning Algorithm for Deep Belief Nets
Showed once again that deep networks can be trained, sparking the revival of deep learning in the 2000s