Title :
Generation of approximation rules using information gain
Author :
Chung, Hong ; Choi, Kyung-Oak ; Chung, Hwan-Mook
Author_Institution :
Dept. of Comput. Eng., Keimyung Univ., Taegu, South Korea
Abstract :
Suggests a method for generating approximation rules by the information gain used in the machine learning by decision tree. We studied that these rules are better than other approximation rules induced by using /spl chi//sup 2/ goodness of fittest or dependency of attributes in rough set theory by an experiment using neural network.
Keywords :
decision trees; entropy; learning (artificial intelligence); neural nets; rough set theory; /spl chi//sup 2/ goodness; approximation rules; attributes; decision tree; dependency; information gain; machine learning; rough set theory; Classification tree analysis; Decision trees; Entropy; Lenses; Level set; Machine learning; Machine learning algorithms; Neural networks; Set theory; Testing;
Conference_Titel :
Fuzzy Systems Conference Proceedings, 1999. FUZZ-IEEE '99. 1999 IEEE International
Conference_Location :
Seoul, South Korea
Print_ISBN :
0-7803-5406-0
DOI :
10.1109/FUZZY.1999.790079
