A learning algorithm for Boltzmann machines

DMCA

A learning algorithm for Boltzmann machines (1985)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by H. Ackley , E. Hinton , J. Sejnowski

Venue:	Cognitive Science
Citations:	573 - 13 self

BibTeX

@ARTICLE{Ackley85alearning,
    author = {H. Ackley and E. Hinton and J. Sejnowski},
    title = {A learning algorithm for Boltzmann machines},
    journal = {Cognitive Science},
    year = {1985},
    pages = {147--169}
}

OpenURL

Abstract

The computotionol power of massively parallel networks of simple processing elements resides in the communication bandwidth provided by the hardware connections between elements. These connections con allow a significant fraction of the knowledge of the system to be applied to an instance of a problem in o very short time. One kind of computation for which massively porollel networks appear to be well suited is large constraint satisfaction searches, but to use the connections efficiently two conditions must be met: First, a search technique that is suitable for parallel networks must be found. Second, there must be some way of choosing internal representations which allow the preexisting hardware connections to be used efficiently for encoding the con-straints in the domain being searched. We describe a generol parallel search method, based on statistical mechanics, and we show how it leads to a gen-eral learning rule for modifying the connection strengths so as to incorporate knowledge obout o task domain in on efficient way. We describe some simple examples in which the learning algorithm creates internal representations thot ore demonstrobly the most efficient way of using the preexisting connectivity structure. 1.

Keyphrases

learning algorithm boltzmann machine internal representation efficient way parallel network computotionol power short time communication bandwidth statistical mechanic hardware connection preexisting hardware connection large constraint satisfaction search gen-eral learning rule search technique significant fraction connection strength preexisting connectivity structure simple processing element simple example generol parallel search method task domain

DMCA