Academic journal article Memory & Cognition

Individual Differences in Category Learning: Memorization versus Rule Abstraction

Academic journal article Memory & Cognition

Individual Differences in Category Learning: Memorization versus Rule Abstraction

Article excerpt

Published online: 15 October 2014

© Psychonomic Society, Inc. 2014

Abstract Although individual differences in categorylearning tasks have been explored, the observed differences have tended to represent different instantiations of general processes (e.g., learners rely upon different cues to develop a rule) and their consequent representations. Additionally, studies have focused largely on participants' categorizations of transfer items to determine the representations that they formed. In the present studies, we used a convergentmeasures approach to examine participants' categorizations of transfer items in addition to their self-reported learning orientations and response times on transfer items, and in doing so, we garnered evidence that qualitatively distinct approaches in explicit strategies for category learning (i.e., memorization vs. abstracting an articulable rule) and consequent representations might emerge in a single task. Participants categorized instances that followed a categorization rule (in Study 1, we used a relational rule; in Study 2, an additional task with a single-feature rule). Critically, for both tasks, some transfer items differed from trained instances on only one attribute (but otherwise were perceptually similar), rendering the item a member of the opposing category on the basis of the rule (i.e., termed ambiguous items). Some learners categorized ambiguous items on the basis of perceptual similarity, whereas others categorized them on the basis of an abstracted rule. Self-reported learning orientation (i.e., memorization vs. rule abstraction) predicted categorizations and response times on transfer items. Differences in learning orientations were not associated with performance on other cognitive measures (i.e., working memory capacity and Raven's Advanced Progressive Matrices). This work suggests that individuals may have different predispositions toward memorization versus rule abstraction in a single categorization task.

Keywords Category learning . Exemplar based processes . Rule learning . Individual differences . Categorization

Within the domain of category learning, two prominent opposing approaches have received considerable attention. An exemplar-based approach assumes that learners' representations are the set of exemplars encountered from each category, and that subsequent classification for new instances is based on similarity to the stored exemplars. This approach has generally been favored for low-structure tasks without clear rules and with few exemplars (see Ashby & Ell, 2001; Smith & Minda, 1998). By contrast, according to a rule-based approach, learners acquire a rule that determines categorization, and that rule is applied for subsequent classifications of new instances. This approach has typically been favored for high-structure tasks in which a logical rule determines categorization (e.g., Bourne, 1974; Little, Nosofsky, & Denton, 2011; Nosofsky, Palmeri, & McKinley, 1994). Work has demonstrated, however, that exemplar processes can be present even when categorical structure is clearly defined by a rule (Medin, 1989; Medin & Smith, 1981; Nosofsky, 1984, 1986, 1987; Regehr & Brooks, 1993), and that rule-based processing can persist even when there are clear exceptions to the rule (Nosofsky et al., 1994).

Although category structures and task demands promote reliance on different category-learning processes, many models of category learning attempt to account for categorization by adopting a single learning orientation across a variety of circumstances. Models that rely exclusively either on exemplar processes (e.g., ALCOVE; Kruschke, 1992) or on rule-based processes (e.g., Ashby, Alfonso-Reese, Turken, & Waldron, 1998; Ashby & Gott, 1988; Ashby & Townsend, 1986) have been developed to account for categorization across all (or nearly all) category structures. These models have promoted research focused on settling whether exemplar- or rule-based approaches are the most fruitful for characterizing how humans learn and represent categories. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.