DMCA
Connectionist models of categorization: a dynamical approach to cognition (1998)
| Citations: | 9 - 7 self |
BibTeX
@TECHREPORT{Tijsseling98connectionistmodels,
author = {Adriaan Geroldus Tijsseling and Adriaan Geroldus Tijsseling},
title = {Connectionist models of categorization: a dynamical approach to cognition},
institution = {},
year = {1998}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The functional role of altered similarity structure in categorization is analyzed. ‘Categorical Perception ’ (CP) occurs when equal-sized physical differences in the signals arriving at our sensory receptors are perceived as smaller within categories and larger between categories (Harnad, 1987). Our hypothesis is that it is by modifying the similarity between internal representations that successful categorization is achieved. This effect depends in part on the iconicity of the inputs, which induces a similarity preserving structure in the internal representations. Categorizations based on the similarity between stimuli are easier to learn than contra-iconic categorization; it is mainly to modify the latter in the service of categorization that the characteristic compression/separation of CP occurs. This hypothesis was tested in a series of neural net simulations of studies on category learning in human subject. The nets are first pre-exposed to the inputs and then given feedback on their performance. The behavior of the resulting networks was then analyzed and compared to human performance. Before it is given feedback, the network discriminates and categorizes input based
Keyphrases
dynamical approach connectionist model internal representation functional role category learning human performance network discriminates sensory receptor contra-iconic categorization equal-sized physical difference categorical perception neural net simulation successful categorization altered similarity structure characteristic compression separation similarity preserving structure human subject
