Atomistic learning in non-modular systems

Philosophical Psychology 18 (3):313-325 (2005)
  Copy   BIBTEX


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?



    Upload a copy of this work     Papers currently archived: 92,323

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library


Added to PP

480 (#40,435)

6 months
10 (#277,276)

Historical graph of downloads
How can I increase my downloads?