Multilayer cluster neural network for totally unconstrained handwritten numeral recognition

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

In this paper, we propose a simple multilayer cluster neural network with five independent subnetworks for off-line recognition of totally unconstrained handwritten numerals. We also show that the use of genetic algorithms for avoiding the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique reduces error rates. In order to verify the performance of the proposed multilayer cluster neural network, experiments with unconstrained handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. For the case of determining the initial weights of the multilayer cluster neural network randomly, the error rates were 2.90%, 1.50%, and 0.80%, respectively. And, for the case of determining the initial weights using a genetic algorithm, the error rates were 2.20%, 0.87%, and 0.60%, respectively.

Original languageEnglish
Pages (from-to)783-792
Number of pages10
JournalNeural Networks
Volume8
Issue number5
DOIs
Publication statusPublished - 1995 Jan 1

Fingerprint

Multilayers
Neural networks
Telecommunications
Weights and Measures
Korea
Canada
Japan
Genetic algorithms
Databases
Telecommunication
Electronic equipment
Experiments

Keywords

  • Genetic algorithm
  • Multilayer cluster neural network
  • Totally unconstrained handwritten numeral recognition

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)
  • Cognitive Neuroscience

Cite this

Multilayer cluster neural network for totally unconstrained handwritten numeral recognition. / Lee, Seong Whan.

In: Neural Networks, Vol. 8, No. 5, 01.01.1995, p. 783-792.

Research output: Contribution to journalArticle

@article{80657f61efc042d58d9ba3af55078c4b,
title = "Multilayer cluster neural network for totally unconstrained handwritten numeral recognition",
abstract = "In this paper, we propose a simple multilayer cluster neural network with five independent subnetworks for off-line recognition of totally unconstrained handwritten numerals. We also show that the use of genetic algorithms for avoiding the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique reduces error rates. In order to verify the performance of the proposed multilayer cluster neural network, experiments with unconstrained handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. For the case of determining the initial weights of the multilayer cluster neural network randomly, the error rates were 2.90{\%}, 1.50{\%}, and 0.80{\%}, respectively. And, for the case of determining the initial weights using a genetic algorithm, the error rates were 2.20{\%}, 0.87{\%}, and 0.60{\%}, respectively.",
keywords = "Genetic algorithm, Multilayer cluster neural network, Totally unconstrained handwritten numeral recognition",
author = "Lee, {Seong Whan}",
year = "1995",
month = "1",
day = "1",
doi = "10.1016/0893-6080(95)00020-Z",
language = "English",
volume = "8",
pages = "783--792",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Multilayer cluster neural network for totally unconstrained handwritten numeral recognition

AU - Lee, Seong Whan

PY - 1995/1/1

Y1 - 1995/1/1

N2 - In this paper, we propose a simple multilayer cluster neural network with five independent subnetworks for off-line recognition of totally unconstrained handwritten numerals. We also show that the use of genetic algorithms for avoiding the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique reduces error rates. In order to verify the performance of the proposed multilayer cluster neural network, experiments with unconstrained handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. For the case of determining the initial weights of the multilayer cluster neural network randomly, the error rates were 2.90%, 1.50%, and 0.80%, respectively. And, for the case of determining the initial weights using a genetic algorithm, the error rates were 2.20%, 0.87%, and 0.60%, respectively.

AB - In this paper, we propose a simple multilayer cluster neural network with five independent subnetworks for off-line recognition of totally unconstrained handwritten numerals. We also show that the use of genetic algorithms for avoiding the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique reduces error rates. In order to verify the performance of the proposed multilayer cluster neural network, experiments with unconstrained handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. For the case of determining the initial weights of the multilayer cluster neural network randomly, the error rates were 2.90%, 1.50%, and 0.80%, respectively. And, for the case of determining the initial weights using a genetic algorithm, the error rates were 2.20%, 0.87%, and 0.60%, respectively.

KW - Genetic algorithm

KW - Multilayer cluster neural network

KW - Totally unconstrained handwritten numeral recognition

UR - http://www.scopus.com/inward/record.url?scp=0028844689&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028844689&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(95)00020-Z

DO - 10.1016/0893-6080(95)00020-Z

M3 - Article

VL - 8

SP - 783

EP - 792

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 5

ER -