jasko@kenmore.bu.edu (John V. Jaskolski) (04/02/91)
I am looking for a good source of heuristics for building expert system rule-bases. Specifically, I am looking for articles or textbooks which outline the logical heuristics that a "Knowledge Engineer" employs when building a rule-base from a set of data. For example, does the knowledge engineer attempt to come up with the minimal set of maximally inductive rules which accommodate the data and perform the desired task? i.e., What are the constraints that go into building a rule-base; What defines a good rule-base? etc.. I am building a rule-base for the first time and I am wondering if there is a way of assuring some sort of near-optimality.
ntm1169@dsac.dla.mil (Mott Given) (04/03/91)
From article <JASKO.91Apr1130101@kenmore.bu.edu>, by jasko@kenmore.bu.edu (John V. Jaskolski): > > I am looking for a good source of heuristics for building expert > system rule-bases. The best book that I have seen in this area is "Principles of Artificial Intelligence and Expert Systems Development" by David W. Rolston, published by McGraw-Hill. His heuristics are very clearly delineated in the chapters as "Principle number: ... text ...". It would be an interesting exercise for a college class to turn the principles into an expert system advisor for aspiring knowledge engineers. -- Mott Given @ Defense Logistics Agency Systems Automation Center, DSAC-TMP, Bldg. 27-1, P.O. Box 1605, Columbus, OH 43216-5002 INTERNET: mgiven@dsac.dla.mil UUCP: ...{osu-cis}!dsac!mgiven Phone: 614-238-9431 AUTOVON: 850-9431 FAX: 614-238-9928 I speak for myself