Atomistic learning in non-modular systems

Authors: Blackmon, James; Byrd, David; Cummins, Robert; Poirier, Pierre; Roth, Martin

Source: Philosophical Psychology, Volume 18, Number 3, June 2005 , pp. 313-325(13)

Publisher: Routledge, part of the Taylor & Francis Group

Key:

- Free Content

- New Content

- Subscribed Content

- Free Trial Content

Abstract:

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'.

Document Type: Research article

DOI: 10.1080/09515080500177283

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$38.49 plus tax Refund Policy