English
Back to timeline

Deep Belief Networks

Era: Revival · 1990s–2010s

Geoffrey Hinton and his colleagues proposed Deep Belief Networks (DBN), with a fast, greedy algorithm that trains them one layer at a time. This layer-wise pre-training helped revive interest in deep neural networks.

Geoffrey Hinton

Status
Verified
Content type
Fact
Sources reviewed

Sources and support

  1. A Fast Learning Algorithm for Deep Belief Nets

    Neural Computation · Source type: Paper

    Hinton, Osindero, and Teh present a fast learning algorithm for deep belief nets.

    Published: ·Accessed: