The Helmholtz machine

Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterized stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative model...

Full description

Saved in:
Bibliographic Details
Published inNeural computation Vol. 7; no. 5; p. 889
Main Authors Dayan, P, Hinton, G E, Neal, R M, Zemel, R S
Format Journal Article
LanguageEnglish
Published United States 01.09.1995
Subjects
Algorithms
Feedback
Humans
Models, Psychological
Pattern Recognition, Automated
Pattern Recognition, Visual
Perception - physiology
Stochastic Processes
Online AccessGet more information

Cover

More Information
Summary:Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterized stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative models, each pattern can be generated in exponentially many ways. It is thus intractable to adjust the parameters to maximize the probability of the observed patterns. We describe a way of finessing this combinatorial explosion by maximizing an easily computed lower bound on the probability of the observations. Our method can be viewed as a form of hierarchical self-supervised learning that may relate to the function of bottom-up and top-down cortical processing pathways.
ISSN:0899-7667
DOI:10.1162/neco.1995.7.5.889