Title :
Visualizing decision table classifiers
Author :
Becker, Barry G.
Author_Institution :
Silicon Graphics Inc., Mountain View, CA, USA
Abstract :
Decision tables, like decision trees or neural nets, are classification models used for prediction. They are induced by machine learning algorithms. A decision table consists of a hierarchical table in which each entry in a higher level table gets broken down by the values of a pair of additional attributes to form another table. The structure is similar to dimensional stacking. A visualization method is presented that allows a model based on many attributes to be understood even by those unfamiliar with machine learning. Various forms of interaction are used to make this visualization more useful than other static designs
Keywords :
data visualisation; decision tables; learning (artificial intelligence); pattern classification; attributes; classification models; decision table classifier visualization; dimensional stacking; hierarchical table; interaction; machine learning algorithms; prediction; Classification tree analysis; Data mining; Data visualization; Decision trees; Displays; Graphics; Layout; Predictive models; Stacking; Training data;
Conference_Titel :
Information Visualization, 1998. Proceedings. IEEE Symposium on
Conference_Location :
Research Triangle, CA
Print_ISBN :
0-8186-9093-3
DOI :
10.1109/INFVIS.1998.729565