Do arbitrary input–output mappings in parallel distributed processing networks require localist coding?

The Parallel Distributed Processing (PDP) approach to cognitive modelling assumes that knowledge is distributed across multiple processing units. This view is typically justified on the basis of the computational advantages and biological plausibility of distributed representations. However, both th...

Descripción completa

Detalles Bibliográficos
Publicado en:Language, Cognition & Neuroscience Vol. 32; no. 3; pp. 392 - 400
Autores principales: Vankov, Ivan I., Bowers, Jeffrey S.
Formato: Journal Article
Publicado: Taylor & Francis Ltd Apr2017
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=120999866&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 120999866
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        23273798
        IQ6T
      jtl: Language, Cognition & Neuroscience
      issn: 23273798
      maglogo: N
    pubinfo:
      dt: Apr2017
      vid: 32
      iid: 3
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        120999866
        10.1080/23273798.2016.1256490
        120999866
      ppf: 392
      ppct: 8
      formats:
      tig:
        atl: Do arbitrary input–output mappings in parallel distributed processing networks require localist coding?
      aug:
        au:
          Vankov, Ivan I.
          Bowers, Jeffrey S.
        affil: Department of Cognitive Science and Psychology, New Bulgarian University, Sofia, Bulgaria
      sug:
      ab: The Parallel Distributed Processing (PDP) approach to cognitive modelling assumes that knowledge is distributed across multiple processing units. This view is typically justified on the basis of the computational advantages and biological plausibility of distributed representations. However, both these assumptions have been challenged. First, there is growing evidence that some neurons respond to information in a highly selective manner. Second, it has been demonstrated that localist representations are better suited for certain computational tasks. In this paper, we continue this line of research by investigating whether localist representations are learned in tasks involving arbitrary input–output mappings. The results imply that the pressure to learn local codes in such tasks is weak, but still there are conditions under which feed-forward PDP networks learn localist representation. Our findings further challenge the assumption that PDP modelling always goes hand in hand with distributed representations and provide directions for future research.
      pubtype: Academic Journal
      doctype: Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N