T. Yamauchi, B.C. Love, & A.B. Markman
Learning nonlinearly separable categories by
inference and classification.
Journal of Experimental Psychology:
Learning, Memory, and Cognition Volume 28, Number 3 (2002)
Previous research suggests that learning categories by classifying new instances highlights information that is useful for discriminating between categories. In contrast learning categories by making predictive inferences focuses learners on an abstract summary of each category (e.g., the prototype). To test this characterization of classification and inference learning further, we evaluated the two learning procedures with nonlinearly separable categories. In contrast to previous research involving cohesive, linearly separable categories, we found that it is more difficult to learn nonlinearly separable categories by making inferences about features than it is to learn them by classifying instances. This finding reflects that the prototype of a nonlinearly separable category does not provide a good summary of the category members. Our results suggest that having a cohesive category structure is more important for inference than it is for classification.
[Download a PDF version of this paper here.]