View in EDS PDF Full Text

Representational Power of Restricted Boltzmann Machines and Deep Belief Networks.

Saved in:
Bibliographic Details
Title: Representational Power of Restricted Boltzmann Machines and Deep Belief Networks.
Authors: Le Roux, Nicolas1 lerouxni@iro.umontreal.ca, Bengio, Yoshua1 bengioy@iro.umontreal.ca
Source: Neural Computation. Jun2008, Vol. 20 Issue 6, p1631-1649. 19p. 1 Diagram, 1 Graph.
Subjects: Artificial neural networks, Functional representation, Computer programming, Artificial intelligence, Algorithms
Abstract: Deep belief networks (DBN) are generative neural network models with many layers of hidden explanatory factors, recently introduced by Hinton,Osindero, and Teh (2006) alongwith a greedy layer-wise unsupervised learning algorithm. The building block of a DBN is a probabilistic model called a restricted Boltzmann machine (RBM), used to represent one layer of the model. Restricted Boltzmann machines are interesting because inference is easy in them and because they have been successfully used as building blocks for training deeper models. We first prove that adding hidden units yields strictly improvedmodeling power,while a second theorem shows that RBMs are universal approximators of discrete distributions. We then study the question of whether DBNs with more layers are strictly more powerful in terms of representational power. This suggests a new and less greedy criterion for training RBMs within DBNs. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 31738341
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Representational Power of Restricted Boltzmann Machines and Deep Belief Networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Le+Roux%2C+Nicolas%22">Le Roux, Nicolas</searchLink><relatesTo>1</relatesTo><i> lerouxni@iro.umontreal.ca</i><br /><searchLink fieldCode="AR" term="%22Bengio%2C+Yoshua%22">Bengio, Yoshua</searchLink><relatesTo>1</relatesTo><i> bengioy@iro.umontreal.ca</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Jun2008, Vol. 20 Issue 6, p1631-1649. 19p. 1 Diagram, 1 Graph.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Functional+representation%22">Functional representation</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+programming%22">Computer programming</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Deep belief networks (DBN) are generative neural network models with many layers of hidden explanatory factors, recently introduced by Hinton,Osindero, and Teh (2006) alongwith a greedy layer-wise unsupervised learning algorithm. The building block of a DBN is a probabilistic model called a restricted Boltzmann machine (RBM), used to represent one layer of the model. Restricted Boltzmann machines are interesting because inference is easy in them and because they have been successfully used as building blocks for training deeper models. We first prove that adding hidden units yields strictly improvedmodeling power,while a second theorem shows that RBMs are universal approximators of discrete distributions. We then study the question of whether DBNs with more layers are strictly more powerful in terms of representational power. This suggests a new and less greedy criterion for training RBMs within DBNs. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=31738341
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1162/neco.2008.04-07-510
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 1631
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Functional representation
        Type: general
      – SubjectFull: Computer programming
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Algorithms
        Type: general
    Titles:
      – TitleFull: Representational Power of Restricted Boltzmann Machines and Deep Belief Networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Le Roux, Nicolas
      – PersonEntity:
          Name:
            NameFull: Bengio, Yoshua
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2008
              Type: published
              Y: 2008
          Identifiers:
            – Type: issn-print
              Value: 08997667
          Numbering:
            – Type: volume
              Value: 20
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Neural Computation
              Type: main
ResultId 1