Research Project Name
Learning by Natural Instruction: Apprenticeship Learning,
Critiquing, and Question-Answering
Objective
The overall objective of this project is a cognitively-plausible computational model of knowledge-intensive
apprenticeship learning expertise in medical decision-making domains. This
objective is being achieved by experimenting with different knowledge
representation and inference architectures, and measuring the extent that they
naturally support the "multiple dimensions of
expertise", such as apprenticeship learning, critiquing, and question-answering.
Approach
How does one capture the architecture of human higher-level cognition
for knowledge-intensive decision making? What
is the correct level of abstraction? Our approach originated from the
observation that when an expert is able to solve a decision-making problem, they
can immediately use their expertise in a large variety of ways.
We refer to the large number of ways that an expert can use their expertise as
the "multiple dimensions of expertise". The ones we have concentrated on are as
follows. First, problem solving, such as medical diagnosis and ship damage
control. Second, teaching their expertise, by presenting problems to students
and critiquing the students solutions. Third, critiquing other experts who are
solving a problem in the same domain. Fourth, apprenticeship learning, wherein
they observe problem solving or their problem solving is observed, such as a
medical internship. Fifth, a post-session question-answering
spoken
dialogue, wherein the ask or answer questions in a dialogue with
another expert. Sixth, learning by resolving
gaps in its expertise during problem solving, by using induction over past
problem cases they have seen. These "multiple dimensions of
expertise" are usually free side-effects of learning to solve problems at an
expert level. They goal is to produce an integrated architecture that yields
them as a free side-effect.
Results
Over the last 25
years,
a succession of systems have been implemented that progressively have
come closer to the overall objective. They include Odysseus,
Odysseus2, Minerva, TIPN, and
Gerona. The major challenge has been to find a method of knowledge
representation and inference that yields the desired multiple dimensions of
expertise. The key issue has been learnability (by apprenticeship, critiquing,
Q/A) via natural instruction.
Selected Publications
GENERAL OVERVIEW
-
Wilkins, D. C. and Fried, D., "Multi-Agent Architectures that
Facilitate Apprenticeship Learning for Real-Time Decision Making:
Minerva and Gerona," AAAI Fall Symposium on Mixed-Initiative
Problem-Solving Agents, Washington D. C., November 3-6, 2005.
Invited Paper. pdf
ODYSSEUS
- Wilkins, D. C., Clancey, W. J. and Buchanan, B. G., "An
Overview of the Odysseus Learning Apprentice," in Machine
Learning: A Guide to Current Research, T. M. Mitchell, J. G.
Carbonell and R. S. Michalski (eds.), Hingham, MA: Kluwer Academic,
1986, 369–373.
pdf
- Wilkins, D. C., Clancey, W. J. and Buchanan, B. J., "Knowledge
Base Refinement By Monitoring Abstract Control Knowledge,"
International Journal of Man-Machine Studies, volume 27, 1987,
281–293.
pdf
- Wilkins, D. C. "Apprenticeship Learning Techniques for Knowledge Based Systems,"
Ph.D. Dissertation, Department of Computer Science and Engineering, University of Michigan, Ann Arbor,
Dec 1987. Also published as: Report STAN-CS-88-1242, Department of Computer Science, Stanford University, December 1988, 155 pages.
pdf
- Wilkins, D. C., "Knowledge Base Refinement Using
Apprenticeship Learning Techniques," Proceedings of the Seventh
National Conference on Artificial Intelligence, Saint Paul,
Minneapolis, August 21–26, 1988, Morgan Kaufmann, 646-651.
pdf
- Wilkins, D. C., "Knowledge Base Refinement as Improving an
Incorrect and Incomplete Domain Theory," in Machine Learning: An
Artificial Intelligence Approach, Volume III, Y. Kodratoff and R.
Michalski (eds.), Morgan Kaufmann, 1990, 493–513.
pdf
ODYSSEUS2, MINERVA
- Donoho, S. and Wilkins, D. C., "Odysseus2: Addressing the
Challenges of Apprenticeship," Eighth Knowledge Acquisition
for Knowledge-Based Systems Workshop, Banff, Canada, pp.
14.1--14.18, January 1994.
pdf
- Park, Y. T. and Donoho, S., and Wilkins, D. C., "Recursive
Heuristic Classification," International Journal of Expert
Systems, Volume 7, Number 4, 1994, 329-357.
pdf
TIPN
- Bulitko, V. and Wilkins, D.C., "Qualitative Simulation of Temporal
Concurrent Processes Using Time Interval Petri Networks," Artificial
Intelligence, Volume 144, Issue 1-2, 95-145, March 2003.
pdf
-
Bulitko, V. and Wilkins, D. C., "ML-TIPN: An Algorithm for
Automated Acquisition of Domain Models based on Time Interval Petri
Nets," Journal of Multi-Valued Logic and Soft Computing,
Volume 12, December, 2006, pp 391-407.
pdf
GERONA
- Fried, D. M., Wilkins, D. C., Grois, E., Peters, S., Schultz, K. and
Clark, B. “The Gerona Knowledge Ontology and It’s Support for Spoken
Dialogue Tutoring of Crisis Decision Making Skills,” Workshop on Knowledge
and Reasoning in Practical Dialogue Systems, Eighteenth International
Joint Conference on Artificial Intelligence, IJCAI-03, August 2003.
pdf
-
Wilkins, D. C. and Fried, D., "Multi-Agent Architectures that
Facilitate Apprenticeship Learning for Real-Time Decision Making:
Minerva and Gerona," AAAI Fall Symposium on Mixed-Initiative
Problem-Solving Agents, Washington D. C., November 3-6, 2005.
Invited Paper. pdf