Supervised versus unsupervised categorization: Two sides of the same coin?

Abstract

Supervised and unsupervised categorization have been studied in separate research traditions. A handful of studies have attempted to explore a possible convergence between the two. The present research builds on these studies, by comparing the unsupervised categorization results of Pothos et al. (2011; Pothos et al., 2008) with the results from two procedures of supervised categorization. In two experiments, we tested 375 participants with nine different stimulus sets and examined the relation between ease of learning of a classification, memory for a classification, and spontaneous preference for a classification. After taking into account the role of the number of category labels (clusters) in supervised learning, we found the three variables to be closely associated with each other. Our results provide encouragement for researchers seeking unified theoretical explanations for supervised and unsupervised categorization, but raise a range of challenging theoretical questions.

Keywords:

• Supervised categorization
• Unsupervised categorization
• Categorization models

Acknowledgments

This research was supported by Economic and Social Research Council (ESRC) Grant R000222655 to E.M.P.

Notes

¹ The presence of the stimulus characteristic corresponding to the intended category label in Love's (2002) stimuli would have led to a stimulus dimension that would enable a perfectly linearly separable classification even in the XOR example of Shepard et al. (1961). It is not clear whether the presence of such a dimension affected performance with the XOR classification in Love's experiments.

² Shepard et al. (1961) employed a single stimulus set and six different classifications for this stimulus set. But, as Love (2002) augmented the stimuli with an additional feature indicating their intended classification, it is simpler to just talk about six separate stimulus sets in the case of that study.