Knowledge extraction from databases: Design principles of the INLEN system
The architecture of a large-scale system for the discovery of knowledge from facts, INLEN, is described. INLEN combines database, knowledge base, and machine learning methods within a uniform user-oriented framework. Data and various forms of knowledge are managed in a uniform way by using various operators. The system's knowledge is stored as knowledge segments, which are structures that link relational tables with rules, equations and/or hierarchies. A variety of machine learning programs are incorporated into the system to serve as high-level knowledge generation operators. These operators are used for generating various kinds of knowledge about the properties and regularities existing in the data. For example, such operators can hypothesize general rules from facts, determine differences and similarities among groups of facts, propose new variables, create conceptual classifications, determine equations governing numeric variables and the conditions under which the equations apply, and determine a variety of statistical characteristics of the data. The management and discovery operators may be combined into macros or programs for repeated applications or automatic branching.
Unable to display preview. Download preview PDF.
- International Intelligent Systems, Inc., “User's Guide to AURORA 2.0: A Discovery System,” Fairfax VA, International Intelligent Systems, Inc., 1988.Google Scholar
- Kaufman, K., Michalski, R.S. and Kerschberg, L., “An Architecture for Knowledge Discovery from Facts: Integrating Database, Knowledge Base and Machine Learning in INLEN,” submitted to Reports of Machine Learning and Inference Laboratory, 1990.Google Scholar
- Michalski, R.S., “Toward a Unified Theory of Learning: Multistrategy Task-adaptive Learning,” MLI Report No. 90-1, Artificial Intelligence Center, George Mason University, 1990.Google Scholar
- Michalski, R.S., Baskin, A.B. and Spackman, K.A., “A Logic-based Approach to Conceptual Database Analysis,” Sixth Annual Symposium on Computer Applications in Medical Care (SCAMC-6), George Washington University Medical Center, Washington, DC, November 1–2, 1982, pp. 792–796.Google Scholar
- Michalski, R.S., Baskin, A.B., Uhrik, C. and Channic, T., “The ADVISE. 1 Meta-Expert System: The General Design and a Technical Description”, Report No. UIUCDCS-F-87-962, Department of Computer Science, University of Illinois, Urbana IL, Jan. 1987.Google Scholar
- Michalski, R.S. and Larson, J.B., rev. by Chen, K., “Incremental Generation of VL1 Hypotheses: The Underlying Methodology and the Description of the Program AQ11,” Report No. UIUCDCS-F-83-905, Department of Computer Science, University of Illinois, Urbana IL, Jan. 1983.Google Scholar
- Spackman, K.A., “QUIN: Integration of Inferential Operators within a Relational Database,” ISG 83-13, UIUCDCS-F-83-917, M. S. Thesis, Department of Computer Science, University of Illinois, Urbana, 1983.Google Scholar
- Wnek, J. and Michalski, R.S., “A System for Visualization of Learning and Inference Processes,” in preparation.Google Scholar
- Wnek, J., Sarma, J., Wahab, A. and Michalski, R.S., “Comparing Learning Paradigms via Diagrammatic Visualization,” Proceedings of International Symposium on Methodologies of Intelligent Systems ISMIS-90, Ras, Z., Zemankova, M., Emrich, M. (Eds.), Elsevier Press, 1990.Google Scholar