Deep pretraining before AlexNet: the table is set
Before 2012, Hinton, Bengio, and LeCun pushed greedy pretraining, autoencoders, and evidence that deep nets could learn.
2 articles
Hinton
Index of editorial tags and filtered coverage.
2 articles
Index of editorial tags and filtered coverage.
Before 2012, Hinton, Bengio, and LeCun pushed greedy pretraining, autoencoders, and evidence that deep nets could learn.
Rumelhart, Hinton, and Williams popularized gradient descent via error backpropagation in multilayer networks.