Misplaced Pages

This is an old revision of this page, as edited by Qwertyus (talk | contribs) at 20:45, 12 June 2013 (see also RBMs, the training algorithm for which (CD) was inspired by wake-sleep). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

The wake-sleep algorithm is an unsupervised learning algorithm for a multilayer neural network. Training is divided into two phases, "wake" and "sleep". In the "wake" phase, neurons are driven by recognition connections (connections from what would normally be considered an input to what is normally considered an output), while generative connections (those from outputs to inputs) are modified to increase the probability that they would reconstruct the correct activity in the layer below (closer to the sensory input). In the "sleep" phase the process is reversed: neurons are driven by generative connections, while recognition connections are modified to increase the probability that they would produce the correct activity in the layer above (further from sensory input).

See also

• Restricted Boltzmann machine, a type of neural net that is trained with a conceptually similar algorithm]]

External links

• http://www.gatsby.ucl.ac.uk/~dayan/papers/hdfn95.pdf

This artificial intelligence-related article is a stub. You can help Misplaced Pages by expanding it.

• v
• t
• e

• Artificial intelligence stubs
• Machine learning algorithms