English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  The Helmholtz Machine

Dayan, P., Hinton, G., Neal, R., & Zemel, R. (1995). The Helmholtz Machine. Neural computation, 7(5), 889-904. doi:10.1162/neco.1995.7.5.889.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-D6D3-E Version Permalink: http://hdl.handle.net/21.11116/0000-0002-D6D4-D
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Dayan, P1, Author              
Hinton, GE, Author
Neal, RM, Author
Zemel, RS, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: 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.

Details

show
hide
Language(s):
 Dates: 1995-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1162/neco.1995.7.5.889
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neural computation
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, Mass. : MIT Press
Pages: - Volume / Issue: 7 (5) Sequence Number: - Start / End Page: 889 - 904 Identifier: ISSN: 0899-7667
CoNE: https://pure.mpg.de/cone/journals/resource/954925561591