Atomistic Learning in Non-Modular Systems
Blackmon (James), Byrd (David), Cummins (Robert), Poirier (Pierre) & Roth (Martin)
Source: Philosophical Psychology, Vol. 18, No. 3, June 2005, pp. 313–325
Paper - Abstract

Paper StatisticsDisclaimer

    We argue that atomistic learning — learning that requires training only on a novel item to be learned — is problematic for networks in which every weight is available for change in every learning situation. This is potentially significant because atomistic learning appears to be commonplace in humans and most non-human animals. We briefly review various proposed fixes, concluding that the most promising strategy to date involves training on pseudo-patterns along with novel items, a form of learning that is not strictly atomistic, but which looks very much like it ‘from the outside’.

Text Colour Conventions (see disclaimer)

  1. Blue: Text by me; © Theo Todman, 2019
  2. Mauve: Text by correspondent(s) or other author(s); © the author(s)

© Theo Todman, June 2007 - Jan 2019. Please address any comments on this page to File output:
Website Maintenance Dashboard
Return to Top of this Page Return to Theo Todman's Philosophy Page Return to Theo Todman's Home Page