KBS Maintenance as Learning Two-Tiered
Domain Representation *

Gennady Agre

Institute of Information Technologies - Bulgarian Academy of Sciences
Acad. G. Bonchev St. Block 29A, 1113 Sofia, Bulgaria
Email: agre@iinf.bg


Abstract. The paper deals with the problem of improving problem-solving 
behavior of traditional KBS in the course of its real operation
which is a part of the maintenance task. The solution of the problem is
searched in integration of the KBS with a specially designed case-based
reasoning module used for correcting solutions produced by the KBS.
Special attention is paid to the methods of case matching and reconciling 
conflicts between CBR and RBR. The proposed solution for both
problems is based on treating the maintenance task as a problem for
learning two-tiered domain representation. From this view point rules
form the first domain tier reflecting existing strong patterns in the representation 
of domain concepts, while the second tier is formed by the
newly solved cases along with a special domain-dependent procedure for
case matching. The main ideas of the approach are illustrated by the
results of some experiments with the experimental system CoRCase.
References

1.	Aamodt, A.: Knowledge-intensive, integrated approach to problem solving and sustained 
learning. Ph.D. Dissertation, University of Trondheim (1991).
2.	Agre, G.: Improvement of KBS Behavior by Using Problem-Solving Experience.
Ph. Jorrand and V. Sgurev (Eds.), Proc. of the VIth Int. Conference AIMSA 94,
World Scientific Pubi., Singapore (1994) 257266.
3.	Agre, G.: An Approach to Integration of Rule-Based and Case-Based Reasoning.
Problems of Engineering Cybernetics and Robotics, 42, Bulgarian Academy of Sciences, 
Sofia (1995) 4049.
4.	Barsalou, L., Hale, G.: Components of conceptual representation: from feature lists
to recursive frames. I. Van Mechelen, J. Hampton, R.S. Michalsi and P. Theuns
(Eds.) Categories and Concepts - Theoretical Views and Inductive Data Analysis,
Academic Press (1993) 97144.
5.	Bergadano, F., Matwin, S., Michaiski R.S., Zhang, J.: Learning two-tiered description 
of flexible concepts: the POSEIDON system. Machine Learning 8 (1992) 543.
6.	Biberman, Y.: A Contex Similarity Measure. F. Bergadano and L. De Raedt (Eds.)
Machine Learning: ECML-94. LNAJ 784, Springer-Verlag (1994) 4863
7.	Coenen, F., Bench-Capon, T.: Maintenance of Knowledge-Based Systems: Theory,
Techniques and Tools, Academic Press (1993).
8.	Golding A.R., Rosenbloom, P.S.: Improving rule-based systems through case-based
reasoning. Proceedings of the National Conference on Artificial Intelligence, Anaheim, 
MIT Press (1991) 2227.
9.	Hammond, K.: Case-Based Planning: Viewing Planning as a Memory Task. Academic Press (1989).
10.	Iordanova l., Giacometti, A., Vila, A., Amy, B., Reymond, F., Abaoub, L., Dahou
M., Rialle, V.: Shade - A Hybrid System for Diagnosis in Electromyography. Proc.
of IXth Int. Congress on Electromyography, Jerusalem (1992).
11.	Kolodner, J.L.: Extending problem solver capabilities through case-based inference.
Proc. of 4th Workshop on Machine Learning, UC-Irvine, June 22-25 (1987) 167
178.
12.	Markov, Z.: Private communication (1995).
13.	Matwin, S., Plante, B.: A Deductive-Inductive Method For Theory Revision. R.S.
Michalski and Gh. Tecuci (Eds.) Proc. of the First Int. Workshop on Multistrategy
Learning (1991) Harpers Ferry, 160174.
14.	Michalski R.S.: Learning flexible concepts: fundamental ideas and a method based
on two-tiered representation. Y. Kodratoff and R.S. Michalski (Eds.) Machine
Learning: an Artificial Intelligence Approach 3, San Mateo, CA: Morgan Kaufmann (1990) 63111.
15.	Mitchell, T.M., R. Keller, Kedar-Cabelli, S.: Explanation-Based Generalization: A
unifying view. Machine Learning 1 (1986) 4780.
16.	Cost, S., Salzberg, S.: A weighted nearest neighbor algorithm for learning with
symbolic features. Machine Learning 10(1) (1991) 5678.
17.	Stanfill, C., Waltz, D.: Toward memory-based reasoning. Communication of ACM
29(12) (1986) 12131229.
18.	Zhang, J.: Integrating Symbolic and Subsymbolic Approaches in Learning Flexible
Concepts. R.S. Michalski and Gh. Tecuci (Eds.) Proc. of the First Int. Workshop
on Multistrategy Learning, Harpers Ferry (1991) 289304.
19.	Zhang, J.: Selecting Typical Instances in Instance-Based Learning. D. Sleeman and
P. Edwards (Eds.) Machine Learning - Proc. of the Ninth Int. Workshop (ML02),
San Mateo, CA: Morgan Kaufmann (1992) 470479
