Tom McCoy and Tom Griffiths publish paper in Nature Communications

Faculty member Tom McCoy and external collaborator Tom Griffiths (from the Princeton Department of Psychology) have published a paper in Nature Communications. The paper is titled “Modeling rapid language learning by distilling Bayesian priors into artificial neural networks.” It introduces a method for combining the complementary strengths of two popular methods for modeling language learning: Bayesian models (which learn well from small amounts of data) and neural networks (which are effective at capturing the complexity of naturalistic data).