Multitype Pattern Discovery Via AQ21: A Brief Description of the Method and Its Novel Features

Simple item page
dc.contributor.authorWojtusiak, Janusz
dc.contributor.authorMichalski, Ryszard S.
dc.contributor.authorKaufman, Kenneth A.
dc.contributor.authorPietrzykowski, Jaroslaw
dc.date.accessioned2006-11-03T18:17:34Z
dc.date.available2006-11-03T18:17:34Z
dc.date.issued2006-06
dc.description.abstractThe AQ21 program seeks different types of patterns in data and represents them in human-oriented forms resembling natural language descriptions. Because of the latter feature it is called a natural induction program. This feature is achieved by employing a highly expressive representation language, Attributional Calculus, that combines aspects of propositional, predicate and multi-valued logic for the purpose of supporting pattern discovery and inductive learning. This paper briefly describes the pattern discovery mode in AQ21, and several novel abilities seamlessly integrated in it, specifically, to discover different types of attributional patterns depending on the parameter settings, to optimize patterns according to a large number of different pattern quality criteria, to learn rules with exceptions, to determine optimized sets of alternative hypotheses generalizing the same data, and to handle data with missing, irrelevant and/or not-applicable meta-values. The discovered patterns are expressed in the form of attributional rules that are directly interpretable in natural language and are visualized using either general logic diagrams or concept association graphs. The described program features are illustrated by a sample of pattern discovery problems.
dc.description.sponsorshipThis research has been conducted in the Machine Learning and Inference Laboratory of George Mason University, whose research activities have been supported in part by the National Science Foundation Grants No. IIS 9906858 and IIS 0097476, and in part by the UMBC/LUCITE #32 grant.
dc.format.extent3308 bytes
dc.format.extent169616 bytes
dc.format.mimetypetext/xml
dc.format.mimetypeapplication/pdf
dc.identifier.citationWojtusiak, J., Michalski, R. S., Kaufman, K. and Pietrzykowski, J., "Multitype Pattern Discovery Via AQ21: A Brief Description of the Method and Its Novel Features," Reports of the Machine Learning and Inference Laboratory, MLI 06-2, George Mason University, Fairfax, VA, June, 2006.
dc.identifier.urihttps://hdl.handle.net/1920/1496
dc.language.isoen_US
dc.relation.ispartofseriesP 06-2
dc.relation.ispartofseriesMLI 06-2
dc.subjectPattern discovery
dc.subjectData mining
dc.subjectMachine learning
dc.subjectAQ learning
dc.subjectMeta-values
dc.subjectKnowledge visualization
dc.titleMultitype Pattern Discovery Via AQ21: A Brief Description of the Method and Its Novel Features
dc.typeTechnical report

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
06-02.pdf
Size:
165.64 KB
Format:
Adobe Portable Document Format
Download

Collections

Machine Learning and Inference Laboratory, College of Public Health