Title :
VC-Dimension of Rule Sets
Author_Institution :
Dept. of Comput. Eng., Isik Univ., Istanbul, Turkey
Abstract :
In this paper, we give and prove lower bounds of the VC-dimension of the rule set hypothesis class where the input features are binary or continuous. The VC-dimension of the rule set depends on the VC-dimension values of its rules and the number of inputs.
Keywords :
learning (artificial intelligence); set theory; VC-dimension values; binary input features; continuous input features; lower bounds; rule set hypothesis class; Computers; Decision trees; Labeling; Pattern recognition; Statistical learning; Training; Vectors; Rule sets; VC-Dimension;
Conference_Titel :
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location :
Stockholm
DOI :
10.1109/ICPR.2014.615
