Behavioral and Brain Sciences



Short Communication

Prototypes and portability in artificial neural network models


Thomas R. Shultz a1
a1 Department of Psychology, McGill University, Montreal, Quebec, Canada H3A 1B1 shultz@psych.mcgill.ca www.psych.mcgill.ca/labs/lnsc/html/Lab-Home.html

Abstract

The Page target article is interesting because of apparent coverage of many psychological phenomena with simple, unified neural techniques. However, prototype phenomena cannot be covered because the strongest response would be to the first-learned stimulus in each category rather than to a prototype stimulus or most frequently presented stimuli. Alternative methods using distributed coding can also achieve portability of network knowledge.



Metrics