How Do PDP Models Learn Quasiregularity?
Parallel distributed processing (PDP) models have had a profound impact on the study of cognition. One domain in which they have been particularly influential is learning quasiregularity, in which mastery requires both learning regularities that capture the majority of the structure in the input plu...
| Publicado en: | Psychological Review Vol. 120; no. 4; pp. 903 - 917 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
American Psychological Association
Oct2013
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=91815878&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 91815878 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 0033295X PYV jtl: Psychological Review issn: 0033295X maglogo: N pubinfo: dt: Oct2013 vid: 120 iid: 4 pid: 34 pub: American Psychological Association artinfo: ui: 91815878 10.1037/a0034195 ppf: 903 ppct: 14 formats: tig: atl: How Do PDP Models Learn Quasiregularity? aug: au: Woojae Kim Pitt, Mark A. Myung, Jay I. affil: Ohio State University su: Parallel processing Distributed computing Communication network analysis Generalizability theory Perturbation theory sug: subj: Parallel processing Distributed computing Communication network analysis Generalizability theory Perturbation theory keyword: hidden representation network analysis PDP model quasiregularity hidden representation network analysis PDP model quasiregularity ab: Parallel distributed processing (PDP) models have had a profound impact on the study of cognition. One domain in which they have been particularly influential is learning quasiregularity, in which mastery requires both learning regularities that capture the majority of the structure in the input plus learning exceptions that violate the regularities. How PDP models learn quasiregularity is still not well understood. Small- and large-scale analyses of a feedforward, 3-layer network were carded out to address 2 fundamental issues about network functioning: how the model can learn both regularities and exceptions without sacrificing generalizability and the nature of the hidden representation that makes this learning possible. Results show that capacity-limited learning pressures the network to form componential representations, which ensures good generalizability. Small and highly local perturbations of this representational system allow exceptions to be learned while minimally disrupting generalizability. Theoretical and methodological implications of the findings are discussed. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|