Methodology for Building an Intelligent Tutoring System

摘要

Over the past 5 years we have been developing a computer program to teach medical diagnosis. Our research synthesizes and extends results in artificial intelligence (AI), medicine, and cognitive psychology. This paper describes the progression of the research, and explains how theories from these fields are combined in a computational model. The general problem has been to develop an intelligent tutoring system by adapting the MYCIN expert system. This conversion requires a deeper understanding of the nature of expertise and explanation than originally required for developing MYCIN, and a concomitant shift in perspective from simple performance goals to attaining psychological validity in the program's reasoning process. Others have written extensively about the relation of artificial intelligence to cognitive science (e.g., Pylyshyn, Boden). Our purpose here is not to repeat those arguments, but to present a case study which will provide a common point for further discussion. To this end, to help evaluate the state of cognitive science, we will outline our methodology and survey what resources and viewpoints have helped our research. We will also discuss pitfalls that other AI-oriented cognitive scientists may encounter. Finally, we will present some questions coming out of our work which might suggest possible collaboration with other fields of research. (Author)