TY - JOUR
T1 - A self-organizing neural tree for large-set pattern classification
AU - Song, Hee Heon
AU - Lee, Seong Whan
N1 - Funding Information:
Manuscript received May 22, 1996; revised January 2, 1998. This work was supported by the Directed Basic Research Fund of Korea Science and Engineering Foundation under Grant 95-0100-06-01-3 and Creative Research Initiatives of the Korean Ministry of Science and Technology.
PY - 1998
Y1 - 1998
N2 - Neural networks have been successfully applied to various pattern classification problems in terms of their learning ability, high discrimination power, and excellent generalization ability. However, for the case of classifying large-set and complex patterns, the greater part of conventional neural networks suffer from several difficulties such as the determination of the structure and size of the network, the computational complexity, and so on. In this paper, to cope with these difficulties, we propose a structurally adaptive intelligent neural tree (SAINT). The basic idea is to partition hierarchically input pattern space using a tree-structured network which is composed of subnetworks with topology-preserving mapping ability. The main advantage of SAINT is that it attempts to find automatically a network structure and size suitable for the classification of large-set and complex patterns through structure adaptation. Experimental results reveal that SAINT is very effective for the classification of large-set real world handwritten characters with high variations, as well as multilingual, multifont, and multisize large-set characters.
AB - Neural networks have been successfully applied to various pattern classification problems in terms of their learning ability, high discrimination power, and excellent generalization ability. However, for the case of classifying large-set and complex patterns, the greater part of conventional neural networks suffer from several difficulties such as the determination of the structure and size of the network, the computational complexity, and so on. In this paper, to cope with these difficulties, we propose a structurally adaptive intelligent neural tree (SAINT). The basic idea is to partition hierarchically input pattern space using a tree-structured network which is composed of subnetworks with topology-preserving mapping ability. The main advantage of SAINT is that it attempts to find automatically a network structure and size suitable for the classification of large-set and complex patterns through structure adaptation. Experimental results reveal that SAINT is very effective for the classification of large-set real world handwritten characters with high variations, as well as multilingual, multifont, and multisize large-set characters.
KW - Large-set pattern classification
KW - Parameter adaptation
KW - Structurally adaptive intelligent neural tree
KW - Structure adaptation
KW - Topology-preserving mapping
UR - http://www.scopus.com/inward/record.url?scp=0032071920&partnerID=8YFLogxK
U2 - 10.1109/72.668880
DO - 10.1109/72.668880
M3 - Article
C2 - 18252462
AN - SCOPUS:0032071920
SN - 2162-237X
VL - 9
SP - 369
EP - 380
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 3
ER -