Can missing information be also useful?
The inductive reasoning core of a medical expert system is presented. The goal is to generate a knowledge base containing diagnostic rules from an, in some sense incomplete, data base. An algorithm is described which, using the missing information in a special way, generates the required rules. The generated rules also match an appropriate complete data base that is exponentially greater than the original one.
KeywordsTree Form Recursive Call Disjunctive Normal Form Label Tree Algorithm Cover
Unable to display preview. Download preview PDF.
- 1.D. Angluin — C.H. Smith 1983. Inductive Inference: Theory and Methods. Computing Surveys 15, 237–269.Google Scholar
- 2.P. Hájek — T. Havránek 1978. Mechanizing Hypothesis Formation. Mathematical Foundations for a General Theory. Springer-Verlag, Berlin.Google Scholar
- 3.R.S. Michalski 1984. Machine Learning: An Artificial Intelligence Approach. Springer-Verlag, Berlin.Google Scholar
- 4.E. Orlowska 1986. Semantic Analysis of Inductive Reasoning. Theoretical Computer Science 43, 81–89.Google Scholar
- 5.G.D. Plotkin 1970. A Note on Inductive Generalization. Machine Intelligence 5. Elsevier North-Holland, New York, 153–163.Google Scholar
- 6.G.D. Plotkin 1971. A Further Note on Inductive Generalization. Machine Intelligence 6. Elsevier North-Holland, New York, 101–124.Google Scholar
- 7.E. Shapiro 1982. Algorithmic Program Debugging. Ph.D. dissertation, Computer Science Dept., Yale University. Published by M.I.T. Press, 1983.Google Scholar
- 8.J.R. Shoenfield 1967. Mathematical Logic. Addison-Wesley.Google Scholar