A self-organizing neural tree for large-set pattern classification

Hee Heon Song, Seong Whan Lee

Research output: Contribution to journalArticle

52 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)369-380
Number of pages12
JournalIEEE Transactions on Neural Networks
Volume9
Issue number3
DOIs
Publication statusPublished - 1998 Dec 1

Fingerprint

Aptitude
Pattern Classification
Self-organizing
Large Set
Pattern recognition
Character sets
Neural networks
Computational complexity
Topology
Neural Networks
Network Structure
Learning
Classification Problems
Discrimination
Computational Complexity
Partition
Experimental Results
Character

Keywords

  • Large-set pattern classification
  • Parameter adaptation
  • Structurally adaptive intelligent neural tree
  • Structure adaptation
  • Topology-preserving mapping

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Theoretical Computer Science

Cite this

A self-organizing neural tree for large-set pattern classification. / Song, Hee Heon; Lee, Seong Whan.

In: IEEE Transactions on Neural Networks, Vol. 9, No. 3, 01.12.1998, p. 369-380.

Research output: Contribution to journalArticle

@article{50be2b48931447c3b7d993edb32394fa,
title = "A self-organizing neural tree for large-set pattern classification",
abstract = "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.",
keywords = "Large-set pattern classification, Parameter adaptation, Structurally adaptive intelligent neural tree, Structure adaptation, Topology-preserving mapping",
author = "Song, {Hee Heon} and Lee, {Seong Whan}",
year = "1998",
month = "12",
day = "1",
doi = "10.1109/72.668880",
language = "English",
volume = "9",
pages = "369--380",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "3",

}

TY - JOUR

T1 - A self-organizing neural tree for large-set pattern classification

AU - Song, Hee Heon

AU - Lee, Seong Whan

PY - 1998/12/1

Y1 - 1998/12/1

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

UR - http://www.scopus.com/inward/citedby.url?scp=0032071920&partnerID=8YFLogxK

U2 - 10.1109/72.668880

DO - 10.1109/72.668880

M3 - Article

C2 - 18252462

AN - SCOPUS:0032071920

VL - 9

SP - 369

EP - 380

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 3

ER -