A RULE-PLUS-EXCEPTION MODEL FOR CLASSIFYING OBJECTS IN CONTINUOUS-DIMENSION SPACES

The authors propose a rule-plus-exception (RULEX) model for how observ ers classify stimuli residing in continuous-dimension spaces. The mode l follows in the spirit of the discrete-dimension version of RULEX dev eloped by Nosofsky, Palmeri, and McKinley (1994). According to the mod el, observers learn categories by forming simple logical rules along s ingle dimensions and by remembering occasional exceptions to those rul es. In the continuous-dimension version of RULEX, the rules are formal ized in terms of linear decision boundaries that are orthogonal to the coordinate axes of the psychological space. In addition, a similarity -comparison process governs whether stored exceptions are used to clas sify an object. The model provides excellent quantitative fits both to averaged classification transfer data and to distributions of general izations observed at the individual-participant level The modeling ana lyses suggest that, when multiple rules are available for solving a pr oblem, averaged classification data often represent a probabilistic mi xture of idiosyncratic rule-plus-exception strategies.