Prehistory — From Neural Networks to the TransformerGeoffrey Hinton, Simon Osindero, Yee-Whye TehGeoffrey Hinton
A Fast Learning Algorithm for Deep Belief Nets
A Fast Learning Algorithm for Deep Belief Nets — greedy layer-wise pretraining followed by fine-tuning
Why it matters
Showed once again that deep networks can be trained, sparking the revival of deep learning in the 2000s
Source — Primary sources first; secondary reports are labelled “Press”
Officialcs.toronto.eduhttps://www.cs.toronto.edu/~hinton/absps/fastnc.pdfAdded in Week 35, 2026 · See that week