General Principles for an Intelligent Tutoring Architecture.
Final rept. Jul 85-Jul 89,
CARNEGIE-MELLON UNIV PITTSBURGH PA
Pagination or Media Count:
This report describes the major outcome of our research project which has been a set of ideas for developing intelligent tutoring systems and an architecture for implementing these ideas. The approach is built around developing a production system model of the skill being taught. Declarative instruction is built to communicate the production rules, a model tracing methodology is implemented to monitor their learning, and a knowledge tracing methodology is implemented to guarantee their mastery. The multiple programming languages project was an attempt to build a single architecture based on these ideas which was capable of teaching many different programming languages. It has been used so far to teach LISP, prolog, and pascal at CMU, and NYNEX has adapted it to teach COBOL. Current research is aimed at building tools to extend this architecture to an authoring system for intelligent tutors generally.
- Computer Programming and Software