Competitive Neural Trees for Pattern Classification

• Authors: Sven Behnke and Nicolaos B. Karayiannis

 
• IEEE Transactions on Neural Networks, vol. 09, num. 06, pp. 1352-1369, 1998.

 
• Abstract:
This paper presents competitive neural trees (CNeTs) for pattern classification. The CNeT contains m-ary nodes and grows during learning by using inheritance to initialize new nodes. At the node level, the CNeT employs unsupervised competitive learning. The CNeT performs hierarchical clustering of the feature vectors presented to it as examples, while its growth is controlled by  forward pruning. Because of the tree structure, the prototype in the CNeT close to any example can be determined by searching only a fraction of the tree. This paper introduces different search methods for the CNeT, which are utilized for the training as well as for the recall. The performance of the CNeT is evaluated using the double spiral problem, the IRIS data set, and a vowel recognition task.
 
• Full paper: tnn98.pdf