P. Baffes and R. Mooney. A novel application of theory refinement to student modeling. In American Association for Artificial Intelligence, pages 403--408, 1996.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....not diagnose what it cannot treat. Given the difficulties in compiling a list of bugs, the task of constructing an intervention to deal with these is even more daunting. This calls into question the usefulness of creating bug libraries. However, work by Baffes and Mooney with the ASSERT system[2] has bypassed this problem. They have constructed a learning system that uses a technique called theory refinement to deduce the student s current misconceptions. The system alters a correct expert module until it generates a set of production rules consistent with the student s behavior. However, ....

P. Baffes and R. Mooney. A novel application of theory refinement to student modeling. In American Association for Artificial Intelligence, pages 403--408, 1996.

.... 1989; Vosniadou, 1995; Chi et al. 1994; Anderson, 1985; Simon et al. 1991] and in Artificial Intelligence [Klahr Siegler, 1978; Sage Langley, 1983; Forbus Gentner, 1986; Laird et al. 1983; Rumelhart, 1989; Newell, 1990; Sleeman et al. 1990; Pazzani, 1991; Shultz et al. 1994; Baffes Mooney, 1996; Schmidt Ling, 1996] However, most computational models of human learning, even though interesting under many respects, are based on excessively simplifying assumptions, especially for what concerns representation of knowledge, which is often reduced to a set of simple Condition Action ....

Baffes P. T., and Mooney R. J. (1996). "A Novel Application of Theory Refinement to Student Modelling". Proc. of Thirteenth National Conference on Artificial Intelligence (Portland, OR), pp. 403-408.

....of students using intelligent tutors. A potential advantage of this architecture is to centralize the tutor s reasoning in one component. Research that improves this single piece affects the entire ITS. There has been some progress made at using ML to simplify ITS construction. The ASSERT system(Baffes Mooney 1996) used theory refinement to automatically construct buggy rules, and could build teaching examples Figure 1: Overview of ADVISOR architecture. to show students the fallacy behind their misconceptions. Given the typical difficulty in compiling bug lists(Burton 1982) this could be a substantial ....

Baffes, P., and Mooney, R. 1996. A novel application of theory refinement to student modeling. In Proceedings of American Association for Artificial Intelligence, 403--408.

....not diagnose what it cannot treat. Given the difficulties in compiling a list of bugs, the task of constructing an intervention to deal with these is even more daunting. This calls into question the usefulness of creating bug libraries. However, work by Baffes and Mooney with the ASSERT system[2] has bypassed this problem. They have constructed a learning system that uses a technique called theory refinement to deduce the student s current misconceptions. The system alters a correct expert module until it generates a set of production rules consistent with the student s behavior, i.e. it ....

P. Baffes and R. Mooney. A novel application of theory refinement to student modeling. In American Association for Artificial Intelligence, pages 403-408, 1996.

....approximate minimal syntactic change. Several theory refinement systems use abduction on individual examples to locate faults in a theory and suggest repairs (Ourston Mooney, 1990; Ourston, 1991; Ourston Mooney, 1994; Wogulis Pazzani, 1993; Wogulis, 1994; Baffes Mooney, 1993; Baffes, 1994; Baffes Mooney, 1996; Brunk, 1996) Abduction is the process of inferring cause from effect or constructing a specific set of assumptions that explain observed events. Each of the above systems uses abduction in a slightly different way, but the following discussion summarizes the basic approach. For each individual ....

.... 1994) and determining when repayment is due on a student loan (Brunk, 1996) The approach has also been successfully employed to construct rulebased models of student knowledge for over 50 students using an intelligent tutoring system for teaching concepts in C programming (Baffes, 1994; Baffes Mooney, 1996). In this application, theory refinement was used to modify correct knowledge of the domain to account for errors individual students made on a set of sample test questions. The resulting modifications to the correct knowledge base were then used to generate tailored instructional feedback for ....

[Article contains additional citation context not shown here]

Baffes, P. T., & Mooney, R. J. (1996). A novel application of theory refinement to student modeling.

....embedded simple learning methods in his quadratic tutor in order to model its student s skills and thus influence instructional sequences. Langley and Ohlsson s (1984) ACM drew on methods for learning search control knowledge to model individual student errors in arithmetic, and more recently, Baffes and Mooney (1995) have adapted techniques for theory revision to develop personalized student models using data on programming errors. More generally, Anderson s (1984) technique of model tracing relies on careful observation of student behavior in the same way as adaptive user interfaces, giving advice only when ....

Baffes, P. T., and Mooney, R. J. (1995). A novel application of theory refinement to student modeling.

....of actions. Furthermore, they allow an encoding of domain knowledge (in terms of the higher level features employed) but may overlook other characteristics present in the data. Machine learning researchers have studied modeling of human behavior in the contexts of, for example, automatic tutoring (Baffes Mooney, 1996). This work models a student s understanding of a subject as a set of Horn clauses which defines deviations from the correct theory of the subject. Such a system can work well when the domain theory is sufficiently understood to induce such rules from behavior, but this is often not the case in ....

Baffes, P., & Mooney, R. (1996). A novel application of theory refinement to student modeling. Proceedings of the Thirteenth National Conference on Artificial Intelligence (pp. 403-408). Portland, OR: AAAI Press.

.... in more accurate results than inducing a knowledge base from scratch (Ourston Mooney, 1994; Towell Shavlik, 1993) Several theory refinement systems use abduction on individual examples to locate faults in a theory and suggest repairs (Ourston Mooney, 1990, 1994; Wogulis Pazzani, 1993; Baffes Mooney, 1993, 1996; Brunk, 1996) Each of these systems use abduction in a slightly different way, but the following summarizes the basic approach. For each individual positive example that is not provable from the current theory, abduction is used to determine a set of assumptions that would allow it to be proved. ....

Baffes, P. T., & Mooney, R. J. (1996). A novel application of theory refinement to student modeling. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pp. 403--408 Portland, OR.

.... Algorithms and Systems Several theory refinement systems use abduction on individual examples to locate faults in a theory and suggest repairs (Ourston and Mooney, 1990; Ourston, 1991; Ourston and Mooney, 1994; Wogulis and Pazzani, 1993; Wogulis, 1994; Baffes and Mooney, 1993; Baffes, 1994; Baffes and Mooney, 1996; Brunk, 1996) The ways in which various forms of logical abduction can be used in revising theories is also discussed and reviewed by Dimopoulos and Kakas (1996) however, they do not discuss using abduction to generalize existing clauses by deleting literals (removing antecedents) Different ....

.... 1994) and determining when repayment is due on a student loan (Brunk, 1996) The approach has also been successfully employed to construct rule based models of student knowledge for over 50 students using an intelligent tutoring system for teaching concepts in C programming (Baffes, 1994; Baffes and Mooney, 1996). In this application, theory refinement was used to modify correct knowledge of the domain to account for errors individual students made on a set of sample test questions. The resulting modifications to the correct knowledge base were then used to generate tailored instructional feedback for ....

Baffes, P. T. and R. J. Mooney: 1996, `A Novel Application of Theory Refinement to Student Modeling'. In: Proceedings of the Thirteenth National Conference on Artificial Intelligence. Portland, OR, pp. 403--408.

....Banner also performs well on revising the original promoter theory, but since its structure is already adequate, this problem does not test structure revision. The system also performed well on revising a knowledge base on C programming to model students for an intelligent tutoring system (Baffes Mooney, 1996). Ramachandran (1998) presents complete results. In order to compare to previous results, we generated learning curves in which the data was randomly split into independent training and test sets, systems were trained on the training data, and then tested on classifying the test examples. Results ....

Baffes, P. T., & Mooney, R. J. (1996). A novel application of theory refinement to student modeling. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pp. 403--408 Portland, OR.

.... Towell and Shavlik, 1993 ] Several theory refinement systems use abduction on individual examples to locate faults in a theory and suggest repairs [ Ourston and Mooney, 1990; Ourston, 1991; Ourston and Mooney, 1994; Wogulis and Pazzani, 1993; Wogulis, 1994; Baffes and Mooney, 1993; Baffes, 1994; Baffes and Mooney, 1996; Brunk, 1996 ] Each of these systems use abduction in a slightly different way, but the following discussion summarizes the basic approach. For each individual positive example that is not derivable from the current theory, abduction is applied to determine a set of assumptions that would allow ....

.... ] and determining when repayment is due on a student loan [ Brunk, 1996 ] The approach has also been successfully employed to construct rule based models of student knowledge for over 50 students us ing an intelligent tutoring system for teaching concepts in C programming [ Baffes, 1994; Baffes and Mooney, 1996 ] In this application, theory refinement was used to modify correct knowledge of the domain to account for errors individual students made on a set of sample test questions. The resulting modifications to the correct knowledge base were then used to generate tailored instructional feedback for ....

P. T. Baffes and R. J. Mooney. A novel application of theory refinement to student modeling. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pages 403--408, Portland, OR, August 1996.

No context found.

Baffes, P. T., & Mooney, R. J. (1995). A novel application of theory refinement to student modeling. Proceedings of the Thirteenth National Conference of the American Association for Artificial Intelligence (pp. 403--408). Portland, OR: AAAI Press.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC