The "wake-sleep" algorithm for unsupervised neural networks

Hinton, GE; Dayan, P; Frey, BJ; Neal, RM

doi:10.1126/science.7761831

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

The "wake-sleep" algorithm for unsupervised neural networks

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

http://science.sciencemag.org/content/268/5214/1158.long
(Publisher version)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Hinton, G., Dayan, P., Frey, B., & Neal, R. (1995). The "wake-sleep" algorithm for unsupervised neural networks. Science, 268(5214), 1158-1161. doi:10.1126/science.7761831.

Cite as: https://hdl.handle.net/21.11116/0000-0002-D6BA-B

Abstract

An unsupervised learning algorithm for a multilayer network of stochastic neurons is described. Bottom-up "recognition" connections convert the input into representations in successive hidden layers, and top-down "generative" connections reconstruct the representation in one layer from the representation in the layer above. In the "wake" phase, neurons are driven by recognition connections, and generative connections are adapted to increase the probability that they would reconstruct the correct activity vector in the layer below. In the "sleep" phase, neurons are driven by generative connections, and recognition connections are adapted to increase the probability that they would produce the correct activity vector in the layer above.