View in EDS HTML Full Text PDF Full Text

The importance of situation-specific encodings: analysis of a simple connectionist model of letter transposition effects.

Saved in:
Bibliographic Details
Title: The importance of situation-specific encodings: analysis of a simple connectionist model of letter transposition effects.
Authors: Fang, Shin-Yi, Smith, Garrett, Tabor, Whitney
Source: Connection Science. Jun2018, Vol. 30 Issue 2, p135-159. 25p.
Subjects: Connectionism, Encoding, Cognitive science, Problem solving, Philosophy of mind, Signs & symbols
Abstract: This paper analyses a three-layer connectionist network that solves a translation-invariance problem, offering a novel explanation for transposed letter effects in word reading. Analysis of the hidden unit encodings provides insight into two central issues in cognitive science: (1) What is the novelty of claims of “modality-specific” encodings? and (2) How can a learning system establish a complex internal structure needed to solve a problem? Although these topics (embodied cognition and learnability) are often treated separately, we find a close relationship between them: modality-specific features help the network discover an abstract encoding by causing it to break the initial symmetries of the hidden units in an effective way. While this neural model is extremely simple compared to the human brain, our results suggest that neural networks need not be black boxes and that carefully examining their encoding behaviours may reveal how they differ from classical ideas about the mind-world relationship. [ABSTRACT FROM AUTHOR]
Copyright of Connection Science is the property of Taylor & Francis Ltd 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: Psychology and Behavioral Sciences Collection
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 129059137
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: The importance of situation-specific encodings: analysis of a simple connectionist model of letter transposition effects.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Fang%2C+Shin-Yi%22">Fang, Shin-Yi</searchLink><br /><searchLink fieldCode="AR" term="%22Smith%2C+Garrett%22">Smith, Garrett</searchLink><br /><searchLink fieldCode="AR" term="%22Tabor%2C+Whitney%22">Tabor, Whitney</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Connection+Science%22">Connection Science</searchLink>. Jun2018, Vol. 30 Issue 2, p135-159. 25p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Connectionism%22">Connectionism</searchLink><br /><searchLink fieldCode="DE" term="%22Encoding%22">Encoding</searchLink><br /><searchLink fieldCode="DE" term="%22Cognitive+science%22">Cognitive science</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+solving%22">Problem solving</searchLink><br /><searchLink fieldCode="DE" term="%22Philosophy+of+mind%22">Philosophy of mind</searchLink><br /><searchLink fieldCode="DE" term="%22Signs+%26+symbols%22">Signs & symbols</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper analyses a three-layer connectionist network that solves a translation-invariance problem, offering a novel explanation for transposed letter effects in word reading. Analysis of the hidden unit encodings provides insight into two central issues in cognitive science: (1) What is the novelty of claims of “modality-specific” encodings? and (2) How can a learning system establish a complex internal structure needed to solve a problem? Although these topics (embodied cognition and learnability) are often treated separately, we find a close relationship between them: modality-specific features help the network discover an abstract encoding by causing it to break the initial symmetries of the hidden units in an effective way. While this neural model is extremely simple compared to the human brain, our results suggest that neural networks need not be black boxes and that carefully examining their encoding behaviours may reveal how they differ from classical ideas about the mind-world relationship. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Connection Science is the property of Taylor & Francis Ltd 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=pbh&AN=129059137
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/09540091.2016.1272097
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 25
        StartPage: 135
    Subjects:
      – SubjectFull: Connectionism
        Type: general
      – SubjectFull: Encoding
        Type: general
      – SubjectFull: Cognitive science
        Type: general
      – SubjectFull: Problem solving
        Type: general
      – SubjectFull: Philosophy of mind
        Type: general
      – SubjectFull: Signs & symbols
        Type: general
    Titles:
      – TitleFull: The importance of situation-specific encodings: analysis of a simple connectionist model of letter transposition effects.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Fang, Shin-Yi
      – PersonEntity:
          Name:
            NameFull: Smith, Garrett
      – PersonEntity:
          Name:
            NameFull: Tabor, Whitney
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2018
              Type: published
              Y: 2018
          Identifiers:
            – Type: issn-print
              Value: 09540091
          Numbering:
            – Type: volume
              Value: 30
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Connection Science
              Type: main
ResultId 1