Wake-sleep algorithm
The wake-sleep algorithm is an unsupervised learning algorithm for a multilayer neural network (e.g. sigmoid belief net). It consists of multiple layers, where the higher one contains a representation of data in the one underneath.[1] 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).
History
Wake phase
![[icon]](/wiki/File:Wiki_letter_w_cropped.svg?lang=en){kind=small} | This section is empty. You can help by adding to it. (October 2015) |
Sleep phase
| This section is empty. You can help by adding to it. (October 2015) |
Applications
| This section is empty. You can help by adding to it. (October 2015) |
See also
- Restricted Boltzmann machine, a type of neural net that is trained with a conceptually similar algorithm
References
- ^ Maei, Hamid Reza (25 January 2007). "Wake-Sleep algorithm for Representational Learning". Retrieved 21 October 2015.
External links
 | This artificial intelligence-related article is a stub. You can help Wikipedia by expanding it. |