Bayesian learning theory applied to human cognition

• DOI: 10.1002/wcs.80
• Publication Date: 2010-05-17T15:54:37Z
• Authors: Robert A. Jacobs; John K. Kruschke
• Keywords: Dynamic Bayesian network

Abstract Probabilistic models based on Bayes' rule are an increasingly popular approach to understanding human cognition. Bayesian allow immense representational latitude and complexity. Because they use normative mathematics process those representations, define optimal performance a given task. This article focuses key mechanisms of information processing, provides numerous examples illustrating approaches the study We start by providing overview modeling networks. then describe three types processing operations—inference, parameter learning, structure learning—in both networks is followed discussion important roles prior knowledge active learning. conclude outlining some challenges for cognition that will need be addressed future research. WIREs Cogn Sci 2011 2 8–21 DOI: 10.1002/wcs.80 categorized under: Computer Science > Artificial Intelligence Psychology Learning