Prototypes and portability in artificial neural network models

Authors
Citation
Tr. Shultz, Prototypes and portability in artificial neural network models, BEHAV BRAIN, 23(4), 2000, pp. 493
Citations number
16
Categorie Soggetti
Psycology,"Neurosciences & Behavoir
Journal title
BEHAVIORAL AND BRAIN SCIENCES
ISSN journal
0140525X → ACNP
Volume
23
Issue
4
Year of publication
2000
Database
ISI
SICI code
0140-525X(200008)23:4<493:PAPIAN>2.0.ZU;2-3
Abstract
The Page target article is interesting because of apparent coverage of many psychological phenomena with simple, unified neural techniques. However, p rototype phenomena cannot be covered because the strongest response would b e to the first-learned stimulus in each category rather than to a prototype stimulus or most frequently presented stimuli. Alternative methods using d istributed coding can also achieve portability of network knowledge.