Hostname: page-component-745bb68f8f-d8cs5 Total loading time: 0 Render date: 2025-02-12T00:11:00.208Z Has data issue: false hasContentIssue false
  • English
  • Français

Prospects for automatic recoding of inputs in connectionist learning

Published online by Cambridge University Press:  01 March 1997

Nicolas Szilas  and
Thomas R. Shultz
Nicolas Szilas
Affiliation:
Department of Psychology, McGill University, Montreal, Quebec, Canada H3A 1B1 nicolas@lima.psych.mcgill.cashultz@psych.mcgill.ca www.psych.mcgill.ca/labs/lnsc/html/lab.-home.html www-leibniz.imag.fr/reseaux/szilas/szilas.html
Thomas R. Shultz
Affiliation:
Department of Psychology, McGill University, Montreal, Quebec, Canada H3A 1B1 nicolas@lima.psych.mcgill.cashultz@psych.mcgill.ca www.psych.mcgill.ca/labs/lnsc/html/lab.-home.html www-leibniz.imag.fr/reseaux/szilas/szilas.html
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Clark & Thornton present the well-established principle that recoding inputs can make learning easier. A useful goal would be to make such recoding automatic. We discuss some ways in which incrementality and transfer in connectionist networks could attain this goal.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 20 , Issue 1 , March 1997 , pp. 81 - 82
Copyright
© 1997 Cambridge University Press