Proceedings of the Annual Meeting of the Cognitive Science Society

One goal of cognitive science is to build theories of mentalfunction that predict individual behavior. In this project wefocus on predicting, for individual participants, which specificitems in a list will be remembered at some point in the future.If you want to know if an individual will remember something,one commonsense approach is to give them a quiz or test suchthat a correct answer likely indicates later memory for an item.In this project we attempt to predict later memory without ex-plicit assessments by jointly modeling both neural and behav-ioral data in a computational cognitive model which capturesthe dynamics of memory acquisition and decay. In this paper,we lay out a novel hierarchical Bayesian approach for com-bining neural and behavioral data and present results showinghow fMRI signals recorded during the study phase of a mem-ory task can improve our ability to predict (in held-out data)which items will be remembered or forgotten 72 hours later.