Adaptation of Cue-Specific Learning Rates in Network Models of Human Category Learning
- Mark A. Gluck, Centre for Molecular and Behavioral Neuroscience, Rutgers University
- Paul T. Glauthier, Centre for Molecular and Behavioral Neuroscience, Rutgers University
- Richard S. Sutton, Department of Computing Science, University of Alberta
Recent engineering considerations have prompted an improvement to the least mean squares (LMS) learning rule for training one-layer adaptive networks: incorporating a dynamically modifiable learning rate for each associative weight accellerates overall learning and provides a mechanism for adjusting the salience of individual cues (Sutton, 1992a,b). Prior research has established that the standard LMS rule can characterize aspects of animal learning (Rescorla & Wagner, 1972) and human category learning (Gluck & Bower, 1988a,b). We illustrate here how this enhanced LMS rule is analogous to adding a cue-salience or attentional component to the psychological model, giving the network model a means for discriminating between relevant and irrelevant cues. We then demonstrate the effectiveness of this enhanced LMS rule for modeling human performance in two non-stationary learning tasks for which the standard LMS network model fails to adequately account for the data (Hurwitz, 1990; Gluck, Glauthier, & Sutton, in preparation).
Citation
M. Gluck,
P. Glauthier,
R. Sutton.
"Adaptation of Cue-Specific Learning Rates in Network Models of Human Category Learning". Conference of the Cognitive Science Society (CogSci), pp 540-545, July 1992.
Keywords: |
mechanism, LMS network, discriminating |
Category: |
In Conference |
BibTeX
@incollection{Gluck+al:CogSci92,
author = {Mark A. Gluck and Paul T. Glauthier and Richard S. Sutton},
title = {Adaptation of Cue-Specific Learning Rates in Network Models of Human
Category Learning},
Pages = {540-545},
booktitle = {Conference of the Cognitive Science Society (CogSci)},
year = 1992,
}
Last Updated: May 31, 2007
Submitted by Staurt H. Johnson