You are not currently logged in.
Access JSTOR through your library or other institution:
Vol. 129, No. 2, Representations (Nov., 2001), pp. 185-194
Published by: Springer
Stable URL: http://www.jstor.org/stable/20117176
Page Count: 10
Preview not available
Connectionist networks have been used to model a wide range of cognitive phenomena, including developmental, neuropsychological and normal adult behaviours. They have offered radical alternatives to traditional accounts of well-established facts about cognition. The primary source of the success of these models is their sensitivity to statistical regularities in their training environment. This paper provides a brief description of the connectionist toolbox and how this has developed over the past 2 decades, with particular reference to the problem of reading aloud.
Synthese © 2001 Springer