Fault Tolerant Teaching and Automated Knowledge Assessment

Distance education, reaching students through accessible, high quality, individualized instruction is a major challenge for today’s universities. Increased access to computers and the Internet has made this idea more feasible, but researchers are still working on the most effective ways to deliver individualized instruction in inexpensive, expandable ways. This paper explores the evolution of the promising field of fault tolerant teaching (FTT). When fully developed, fault tolerant teaching systems will automatically assess student knowledge and use this assessment to direct remediation of knowledge. FTT methods use statistical techniques to interpret student responses to questions, and are constructed to tolerate the usual errors that occur during testing – such as a student answering a question correctly without knowing how, or accidentally missing a question they understand well. These methods do not require any knowledge about the instructional topic. This paper presents the evolution of fault tolerant teaching and the promising results of an experiment to test FTT methods.