ALCOVE: An exemplar-based connectionist model of category learning. 论文

1992Psychological Review引用 1625
Child and Animal Learning DevelopmentDomain Adaptation and Few-Shot LearningReading and Literacy Development

详细信息

发表期刊/会议
Psychological Review
发表日期
1992-01-01
发表年份
1992

关键词

Child and Animal Learning DevelopmentDomain Adaptation and Few-Shot LearningReading and Literacy Development

摘要

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.