View in EDS HTML Full Text PDF Full Text

Nonmonotonic Generalization Bias of Gaussian Mixture Models.

Saved in:
Bibliographic Details
Title: Nonmonotonic Generalization Bias of Gaussian Mixture Models.
Authors: Akaho, Shotaro1, Kappen, Hilbert J.2
Source: Neural Computation. Jun2000, Vol. 12 Issue 6, p1411-1427. 17p. 6 Graphs.
Subjects: Artificial neural networks, Temperature measurements, Symmetry breaking, Transport theory
Abstract: Theories of learning and generalization hold that the generalization bias, defined as the difference between the training error and the generalization error, increases on average with the number of adaptive parameters. This article, however, shows that this general tendency is violated for a gaussian mixture model. For temperatures just below the first symmetry breaking point, the effective number of adaptive parameters increases and the generalization bias decreases. We compute the dependence of the neural information criterion on temperature around the symmetry breaking. Our results are confirmed by numerical cross-validation experiments. [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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 3347677
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Nonmonotonic Generalization Bias of Gaussian Mixture Models.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Akaho%2C+Shotaro%22">Akaho, Shotaro</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Kappen%2C+Hilbert+J%2E%22">Kappen, Hilbert J.</searchLink><relatesTo>2</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Jun2000, Vol. 12 Issue 6, p1411-1427. 17p. 6 Graphs.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Temperature+measurements%22">Temperature measurements</searchLink><br /><searchLink fieldCode="DE" term="%22Symmetry+breaking%22">Symmetry breaking</searchLink><br /><searchLink fieldCode="DE" term="%22Transport+theory%22">Transport theory</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Theories of learning and generalization hold that the generalization bias, defined as the difference between the training error and the generalization error, increases on average with the number of adaptive parameters. This article, however, shows that this general tendency is violated for a gaussian mixture model. For temperatures just below the first symmetry breaking point, the effective number of adaptive parameters increases and the generalization bias decreases. We compute the dependence of the neural information criterion on temperature around the symmetry breaking. Our results are confirmed by numerical cross-validation experiments. [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=3347677
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1162/089976600300015439
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 1411
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Temperature measurements
        Type: general
      – SubjectFull: Symmetry breaking
        Type: general
      – SubjectFull: Transport theory
        Type: general
    Titles:
      – TitleFull: Nonmonotonic Generalization Bias of Gaussian Mixture Models.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Akaho, Shotaro
      – PersonEntity:
          Name:
            NameFull: Kappen, Hilbert J.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2000
              Type: published
              Y: 2000
          Identifiers:
            – Type: issn-print
              Value: 08997667
          Numbering:
            – Type: volume
              Value: 12
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Neural Computation
              Type: main
ResultId 1