Abstract

An integrative cognitive architecture provides a computational framework within which to model a broad range of human behavior. It encompasses behavior from perception through cognition to motor action, and integrates performance, learning, and eventually moderator variables like cultural values or fatigue. To model any one behavioral data set using an integrative cognitive architecture can be more bother than it seems to be worth. However, integrative cognitive architectures provide power and constraint to every model, benefits that we believe offset the cost of "architecture overhead". We advocate a procedure for cognitive modeling that uses an integrative cognitive architecture, prior models in that architecture, and a relatively small data set, to gain general insights about a larger domain of interest. We demonstrate this procedure by examining the development of a Soar model of learning and memory in a real-world humancomputer interaction task. Keywords Computational cognitive ...

Citations