Speed-Up, Quality and Competence
in Multi-modal Case-Based Reasoning

Luigi Portinale1, Pietro Torasso2, Paolo Tavano2

1 Dipartimento di Scienze e Tecnologie Avanzate
Universita del Piemonte Orientale A. Avogadro - Alessandria (ITALY)
2 Dipartimento di Informatica
Universita di Torino - Torino (ITALY)




Abstract. The paper discusses the different aspects concerning performance 
arising in multi-modal systems combining Case-Based Reasoning
and Model-Based Reasoning for diagnostic problem solving. In particular, 
we examine the relation among speed-up of problems solving, competence 
of the system and quality of produced solutions. Because of the
well-know utility problem, there is no general strategy for improving all
these parameters at the same time, so the trade-off among such parameters 
must he carefully analyzed. We have developed a case memory
management strategy which allows the interleaving of learning of new
cases with forgetting phases, where useless and potentially dangerous
cases are identified and removed. This strategy, combined with a suitable 
tuning on the precision required for the retrieval of cases (in terms
of estimated adaptation cost), provides an effective mechanism for taking
under control the utility problem. Experimental analysis performed on a
real-world domain shows in fact that improvements over both speed-up
and competence can be obtained, without compromising in a significant
way the quality of solutions.
References

1.	D. Aha and J. Daniels (eds.). Proc. AAAI Workshop on CBR Integrations. AAAI
Press, 1998.
2.	L. Console, L. Portinale, D. Theseider Dupr, and P. Torasso. Combining heuristic
and causal reasoning in diagnostic problem solving. In J.M. David, J.P. Krivine,
and R. Simmons, editors, Second Generation Expert Systems, pages 46,68. Springer
Verlag, 1993.
3.	L. Console and P. Torasso. A spectrum of logical definitions of model-based diagnosis. 
Computational Intelligence, 7(3): 133141, 1991.
4.	B. Freuder (ed.). AAAI Spring Symposium on Multi-modal Reasoning. AAAI
Press, 1998.
5.	A.G. Francis and A. Ram. The utility problem in case-based reasoning. Technical
Report ER-93-08, Georgia Tech, 1993.
6.	5. Minton. Learning effective search control knowledge: an EBL approach. Technical 
Report CMU-CS-88-133, Dept. of Computer Science, Carnagie-Mellon Univ.,
1988.
7.	L. Portinale and P. Torasso. ADAPtER: an integrated diagnostic system combining
case-based and abductive reasoning. In Proc. 1st ICCBR, LNAI 1010, pages 277
288. Springer Verlag, 1995.
8.	L. Portinale and P. Torasso. On the usefulness of re-using diagnostic solutions. In
Proc. 12th European Conf. on AI - ECAI 96, pages 13714 1, Budapest, 1996.
9.	L. Portinale and P. Torasso. Performance issues in ADAPtER a combined CBR-
MBR diagnostic architecture. In Proc. AAAI Spring Sympos. on Multi-Modal
Reasoning, pages 4752, AAAI Press, Stanford, 1998.
10.	L. Portinale, P. Torasso, and D. Magro. Selecting most adaptable diagnostic solutions 
through Pivoting-Based Retrieval. In Proc. 2nd ICCBR, LNAI 1266, pages
393402. Springer Verlag, 1997.
11.	L. Portinale, P. Torasso, and P. Tavano. Dynamic case memory management. In
Proc. ECAI 98, pages 7378, Brighton, 1998.
12.	B. Smyth and P. Cunningham. The utility problem analysed: a case-based reasoning 
perspective. In LNAI 1168, pages 392399. Springer Verlag, 1996.
13.	B. Smyth and M.T. Keane. Remembering to forget. In Proc. 14th IJCAI, pages
377382,	Montreal, 1995.
14.	B. Smyth and E. McKenna. Modeling the competence of case-bases. In Proc. 4th
EWCBR, LNAI 1488, pages 208220. Springer Verlag, 1998.
15.	M. van Someren, J. Surma, and P. Torasso. A utility-based approach to learning in
a mixed case-based and model-based reasoning architecture. In Proc. 2nd ICCBR,
LNAI 1266, pages 477488. Springer Verlag, 1997.
