Pattern recognition with neural networks combined by genetic algorithm

Research output: Contribution to journalArticle

59 Citations (Scopus)

Abstract

Soft computing techniques have been recently exploited as a promising tool for achieving high performance in pattern recognition. This paper presents a hybrid method which combines neural network classifiers by genetic algorithm. Genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs as coefficients. The experimental results with the recognition problem of totally unconstrained handwritten numerals show that the genetic algorithm produces better results than the conventional methods such as averaging and Borda count.

Original languageEnglish
Pages (from-to)339-347
Number of pages9
JournalFuzzy Sets and Systems
Volume103
Issue number2
DOIs
Publication statusPublished - 1999 Apr 16

Fingerprint

Pattern Recognition
Pattern recognition
Genetic algorithms
Genetic Algorithm
Neural Networks
Neural networks
Numeral
Soft computing
Soft Computing
Hybrid Method
Averaging
Count
Classifiers
High Performance
Classifier
Output
Experimental Results
Coefficient

All Science Journal Classification (ASJC) codes

  • Logic
  • Artificial Intelligence

Cite this

@article{f5282e4a0ccf4984aa336585e3f3acc1,
title = "Pattern recognition with neural networks combined by genetic algorithm",
abstract = "Soft computing techniques have been recently exploited as a promising tool for achieving high performance in pattern recognition. This paper presents a hybrid method which combines neural network classifiers by genetic algorithm. Genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs as coefficients. The experimental results with the recognition problem of totally unconstrained handwritten numerals show that the genetic algorithm produces better results than the conventional methods such as averaging and Borda count.",
author = "Sung-Bae Cho",
year = "1999",
month = "4",
day = "16",
doi = "10.1016/S0165-0114(98)00232-2",
language = "English",
volume = "103",
pages = "339--347",
journal = "Fuzzy Sets and Systems",
issn = "0165-0114",
publisher = "Elsevier",
number = "2",

}

Pattern recognition with neural networks combined by genetic algorithm. / Cho, Sung-Bae.

In: Fuzzy Sets and Systems, Vol. 103, No. 2, 16.04.1999, p. 339-347.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pattern recognition with neural networks combined by genetic algorithm

AU - Cho, Sung-Bae

PY - 1999/4/16

Y1 - 1999/4/16

N2 - Soft computing techniques have been recently exploited as a promising tool for achieving high performance in pattern recognition. This paper presents a hybrid method which combines neural network classifiers by genetic algorithm. Genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs as coefficients. The experimental results with the recognition problem of totally unconstrained handwritten numerals show that the genetic algorithm produces better results than the conventional methods such as averaging and Borda count.

AB - Soft computing techniques have been recently exploited as a promising tool for achieving high performance in pattern recognition. This paper presents a hybrid method which combines neural network classifiers by genetic algorithm. Genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs as coefficients. The experimental results with the recognition problem of totally unconstrained handwritten numerals show that the genetic algorithm produces better results than the conventional methods such as averaging and Borda count.

UR - http://www.scopus.com/inward/record.url?scp=0033115883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033115883&partnerID=8YFLogxK

U2 - 10.1016/S0165-0114(98)00232-2

DO - 10.1016/S0165-0114(98)00232-2

M3 - Article

AN - SCOPUS:0033115883

VL - 103

SP - 339

EP - 347

JO - Fuzzy Sets and Systems

JF - Fuzzy Sets and Systems

SN - 0165-0114

IS - 2

ER -