Title :
CNeT: competitive neural trees for pattern classification
Author :
Behnke, Sven ; Karayiannis, Nicolaos B.
Author_Institution :
Dept. of Math. & Comput. Sci., Martin-Luther-Univ., Halle-Wittenberg, Germany
Abstract :
This paper introduces competitive neural trees (CNeT) for pattern classification. The CNeT performs hierarchical classification and employs competitive unsupervised learning at the node level. The generalization ability of the CNeT is guaranteed by forward pruning, which is an inherent part of the learning process. Different search methods are introduced for the CNeT and used for both training and recall. The influence of different search methods on the performance of the CNeT is experimentally evaluated
Keywords :
neural nets; pattern classification; search problems; unsupervised learning; CNeT; competitive neural trees; competitive unsupervised learning; generalization ability; hierarchical classification; pattern classification; recall; search methods; training; Counting circuits; Decision trees; Electronic mail; Mathematics; Neural networks; Pattern classification; Prototypes; Search methods; Testing; Unsupervised learning;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549111
