INSYS 547:
Artificial Intelligence in Education and Training

Goals of Course

In this course, we will:

• Explore potential and limitations of Intelligent Tutoring Systems (ITSs)
• Recognize the sources of errors in intellectual performance
• Use appropriate methods for representing and developing models of human knowledge and intelligence using:Error-based (Buggy)/Mistake-based

  Example-based

  Production rule

  Case-based reasoning

  Semantic nets

• Represent learners'/experts'mental models
• Use knowledge representation methods to design and devlop a prototype of:

  Intelligent help system

  Intelligent agent

  Advice systems in EPSSs

  Diagnostic performance support system

  Model for ILE

  Coaching systems for ILE (e.g. Sherlock)

 
Course Requirements

You need to identify a task domain for which to design and develop tsome combination of the following prototype products:Intelligent help system

• Intelligent agent
• Diagnostic performance support system
• Model for Interactive Learning Environment
• Coaching systems for Interactive Learning Environment
• Microworld or cognitive tool

  You will use the following technologies to produce a:

• Cognitive simulation using an expert system
• Case-based reasoning database
• Schemata simulation using a semnantic net

For each of these assignments, assessment criteria will be negotiated.

Course Topics

• Nature of Intelligence
• Uses of intelligence

diagnose student knowledge structures, skills, styles

Adapt instruction

• Mental Models
• Intelligent Tutoring Systems (ITSs) - Glass Box Representations

student model

domain (expert) model

tutoring model

determine what gets taught next

selectes/generates (using expert model) a problem

situation, simulation, context

• Student Modeling

Internal

External - as models for microworlds, ILEs, cognitive tools

• Models of Knowledge Representation

DECLARATIVE KNOWLEDGE

Schema Based (Semantic nets)

Frames: structured object representation

Example-based

PROCEDURAL KNOWLEDGE

Error-based (Buggy)/Mistake-based

misconceptions/poor conpetual models

deficient knowledge structures

errors, Buggy algorithms, Bug catalogs

Production rule

• EPISODIC MEMORY

Case-based reasoning

• CONNECTIONIST MODELS

Neural nets

• OTHERS

Blackboard models

Formal Logic

• Knowledge Acquisition and Analysis Methods

  Cognitive Task Analysis

  GOMS

  ACT*

  Activity Theory

• Paradigm Shift in Cognitive Psychology: Symbolic Representation vs. Situated Cognition

Text Materials

Benfer, R.A., Brent, E.E.., & Furbee, L. (1991). Expert Systems. CA: Sage Press.

Schank, R.C. (1990). Tell me a story: Narrative and intelligence. Evanston, IL: Northwestern University Press.

Supplementary Texts

Costa, E. (1991). New directions for intelligent turoing systems. Berlin: Springer-Verlag.

Ercoli, P., & Lewis, R. (1987). Artificial intelligence tools in education, Proceedings of the IFIP TC 3 Working Conference on Artificial Intelligence Tools in Education. Amsterdam: North-Holland.

Farr, M.J. & Psotka, J. (1992). Intelligent instruction by computer: Theory and practice. Washington: Taylor & Francis.

Grabinger, R. S. Wilson, B.G. & Jonassen, D.H. (1990). Building expert systems in training and education. New York, Praeger, 1990

Larkin, J.H., & Chabay, R.W. (1992). Computer-assited instruction and intelligent tutoring systems: Shared goals and co[p;lementary approaches. Hillsdale, NJ: Lawrence Erlbaum.

Lawler, R. W., Yazdini M., (Ed.) (1987). Artificial Intelligence and Education: Learning Environments & Tutoring Systems.

Anderson, J.R., Boyle, C.F., Corbett, A.T., & Lewis, M.W. (1990). Cognitive modeling and intelligent tutoring. Artificial Intelligence, 42, 7-49.

Brown, J.S. (1989). Toward a new epistemology for learning. In C. Frasson & J. Gauthier (Eds.), Intelligent Tutoring Systems and the Crossroad of AI Education. Norwood, NJ: Ablex.

Clancey, W., & Soloway, E. (1990). Artificial Intelligence and Learning Environments. Artificial Intelligence, 42, 1-6.

Katz, S., Lesgold, A., Eggan, G., & Gordin, M. (1992). Modeling the Student in Sherlock II. Journal of Artificial Intelligence in Education, 3, 495-518.

Kearsley, G. (1987 Artificial intelligence & education: Applications and methods. Reading, MA: Addison Wesley.

Kolodner, J. (1993). Case-based reasoning. San Mateo, CA: Morgan Kaufman.

Mahar, M.L., Balachandran, M.B., & Zhang, D.M. (1995). Case-based reasoning in design. Hillsdale, NJ: Lawrence Erlbaum

McFarland, T.D. & Reese, P. (1990). Expert systems in education and training. Englewood Cliffs, N.J., Educational Technology Publications, 1990

Reiser, B., Kimberg, D., Lovett, M., & Ranney, M. (1992). Knowledge representation and explanation in GIL, an intelligent tutor for programming. In J. Larkin & C.R. (Eds.), Computer-Assisted Instruction and Intelligent Tutoring Systems: Shared Goals and Complementary Approaches Hillsdale, NJ: Erlbaum.

Schank, R.C., Kass, A., & Riebeck, C.K. (1994). Inside case-based reasoning. Hillsdale, NJ: Lawrence Erlbaum.

Pirolli, P. (1986). A cognitive model and computer tutor. Human-Computer Interaction, 12, 319-355.

Van Lehn, K. (1988). Student modeling. In M.C. Polson & J.J. Richardson (Eds.), Foundations of Intelligent Tutoring Systems Hillsdale, NJ: Lawrence Erlbaum Associates.

Wenger, E. (1987). Artificial Intelligence and Tutoring Systems. Los Altos: Morgan Kaufman.

Winkels, R. (1992) Explorations in Intelligent tutoring and help. Amsterdam: IOS Press.

Yazdani, M., Lawler R., (Ed.) (1991). Artificial Intelligence and Education: Principles and Case Studies. Vol 1. Norwood, NJ: Ablex.

Yazdani, M., Lawler R., (Ed.) (1991). Artificial Intelligence and Education: Principles and Case Studies. Vol 2 Norwood, NJ: Ablex.