ALCOVE: An exemplar-based connectionist model of category learning.
- 1 January 1992
- journal article
- Published by American Psychological Association (APA) in Psychological Review
- Vol. 99 (1) , 22-44
- https://doi.org/10.1037/0033-295x.99.1.22
Abstract
ALCOVE (attention learning covering map) is a connectionist model of category learning that incorporates an exemplar-based representation (Medin & Schaffer, 1978; Nosofsky, 1986) with error-driven learning (Gluck & Bower, 1988; Rumelhart, Hinton, & Williams, 1986). Alcove selectively attends to relevant stimulus dimensions, is sensitive to correlated dimensions, can account for a form of base-rate neglect, does not suffer catastrophic forgetting, and can exhibit 3-stage (U-shaped) learning of high-frequency exceptions to rules, whereas such effects are not easily accounted for by models using other combinations of representation and learning method.Keywords
This publication has 0 references indexed in Scilit: