Brain Mechanisms of Concept Learning

Abstract

Concept learning, the ability to extract commonalities and highlight distinctions across a set of related experiences to build organized knowledge, is a critical aspect of cognition. Previous reviews have focused on concept learning research as a means for dissociating multiple brain systems. The current review surveys recent work that uses novel analytical approaches, including the combination of computational modeling with neural measures, focused on testing theories of specific computations and representations that contribute to concept learning. We discuss in detail the roles of the hippocampus, ventromedial prefrontal, lateral prefrontal, and lateral parietal cortices, and how their engagement is modulated by the coherence of experiences and the current learning goals. We conclude that the interaction of multiple brain systems relating to learning, memory, attention, perception, and reward support a flexible concept-learning mechanism that adapts to a range of category structures and incorporates motivational states, making concept learning a fruitful research domain for understanding the neural dynamics underlying complex behaviors.

Keywords: categorization; computational modeling; fMRI; hippocampus; parietal cortex; prefrontal cortex.

Figure 1.

Concept representations per the exemplar and prototype models. Exemplar model assumes that categories are represented by specific exemplars. Prototype model assumes that categories are represented by their central tendency (prototype), which is abstracted from specific exemplars and embodies all characteristic features.

Figure 2.

A schematic depiction of results from Wutz et al. (2018). Distinct neural circuits communicate through distinct channels when concept learning requires low levels of abstraction versus high levels of abstraction.