Gradualness Facilitates Knowledge Refinement
Author:
- 1 September 1985
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PAMI-7 (5) , 523-530
Abstract
To facilitate knowledge refinement, a system should be designed so that small changes in the knowledge correspond to small changes in the function or performance of the system. Two sets of experiments show the value of small, heuristically guided changes in a weighted rule base. In the first set, the ordering among numbers (reflecting certainties) makes their manipulation more straightforward than the manipulation of relationships. A simple credit assignment and weight adjustment strategy for improving numbers in a weighted, rule-based expert system is presented. In the second set, the rearrangement of predicates benefits from additional knowledge about the ``ordering'' among predicates. A third set of experiments indicates the importance of the proper level of granularity when augmenting a knowledge base. Augmentation of one knowledge base by analogical reasoning from another knowledge base did not work with only binary relationships, but did succeed with ternary relationships. To obtain a small improvement in the knowledge base, a substantial amount of structure had to be treated as a unit.Keywords
This publication has 17 references indexed in Scilit:
- Online searching styles: A case‐study‐based model of searching behaviorJournal of the American Society for Information Science, 1984
- Testing of a natural language retrieval system for a full text knowledge baseJournal of the American Society for Information Science, 1984
- Using empirical analysis to refine expert system knowledge basesArtificial Intelligence, 1984
- Learning by Experimentation: Acquiring and Refining Problem-Solving Heuristics1983
- Learning by Analogy: Formulating and Generalizing Plans from Past Experience1983
- The nature of heuristicsArtificial Intelligence, 1982
- Generalization as searchArtificial Intelligence, 1982
- Evolution and gradualnessBioSystems, 1981
- Medline: An introduction to on‐line searchingJournal of the American Society for Information Science, 1980
- Bootstrapping on the adaptive landscapeBioSystems, 1979