View in EDS HTML Full Text PDF Full Text

Adaptive Learning Algorithm Convergence in Passive and Reactive Environments.

Saved in:
Bibliographic Details
Title: Adaptive Learning Algorithm Convergence in Passive and Reactive Environments.
Authors: Golden, Richard M.1 golden@utdallas.edu
Source: Neural Computation. Oct2018, Vol. 30 Issue 10, p2805-2832. 28p.
Subjects: Instructional systems, Passive learning, Active learning, Artificial neural networks, Machine learning, Deep learning, Stochastic approximation, Stochastic convergence
Abstract: Although the number of artificial neural network and machine learning architectures is growing at an exponential pace, more attention needs to be paid to theoretical guarantees of asymptotic convergence for novel, nonlinear, high-dimensional adaptive learning algorithms. When properly understood, such guarantees can guide the algorithm development and evaluation process and provide theoretical validation for a particular algorithm design. For many decades, the machine learning community has widely recognized the importance of stochastic approximation theory as a powerful tool for identifying explicit convergence conditions for adaptive learning machines. However, the verification of such conditions is challenging for multidisciplinary researchers not working in the area of stochastic approximation theory. For this reason, this letter presents a new stochastic approximation theorem for both passive and reactive learning environments with assumptions that are easily verifiable. The theorem is widely applicable to the analysis and design of important machine learning algorithms including deep learning algorithms with multiple strict local minimizers, Monte Carlo expectation-maximization algorithms, contrastive divergence learning in Markov fields, and policy gradient reinforcement learning. [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: 131937520
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Adaptive Learning Algorithm Convergence in Passive and Reactive Environments.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Golden%2C+Richard+M%2E%22">Golden, Richard M.</searchLink><relatesTo>1</relatesTo><i> golden@utdallas.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Oct2018, Vol. 30 Issue 10, p2805-2832. 28p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Instructional+systems%22">Instructional systems</searchLink><br /><searchLink fieldCode="DE" term="%22Passive+learning%22">Passive learning</searchLink><br /><searchLink fieldCode="DE" term="%22Active+learning%22">Active learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+approximation%22">Stochastic approximation</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+convergence%22">Stochastic convergence</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Although the number of artificial neural network and machine learning architectures is growing at an exponential pace, more attention needs to be paid to theoretical guarantees of asymptotic convergence for novel, nonlinear, high-dimensional adaptive learning algorithms. When properly understood, such guarantees can guide the algorithm development and evaluation process and provide theoretical validation for a particular algorithm design. For many decades, the machine learning community has widely recognized the importance of stochastic approximation theory as a powerful tool for identifying explicit convergence conditions for adaptive learning machines. However, the verification of such conditions is challenging for multidisciplinary researchers not working in the area of stochastic approximation theory. For this reason, this letter presents a new stochastic approximation theorem for both passive and reactive learning environments with assumptions that are easily verifiable. The theorem is widely applicable to the analysis and design of important machine learning algorithms including deep learning algorithms with multiple strict local minimizers, Monte Carlo expectation-maximization algorithms, contrastive divergence learning in Markov fields, and policy gradient reinforcement learning. [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=131937520
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1162/neco_a_01117
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 2805
    Subjects:
      – SubjectFull: Instructional systems
        Type: general
      – SubjectFull: Passive learning
        Type: general
      – SubjectFull: Active learning
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Stochastic approximation
        Type: general
      – SubjectFull: Stochastic convergence
        Type: general
    Titles:
      – TitleFull: Adaptive Learning Algorithm Convergence in Passive and Reactive Environments.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Golden, Richard M.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2018
              Type: published
              Y: 2018
          Identifiers:
            – Type: issn-print
              Value: 08997667
          Numbering:
            – Type: volume
              Value: 30
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Neural Computation
              Type: main
ResultId 1