Order filtering neural network

Chi Ming Chen, Jar-Ferr Yang

Research output: Contribution to journalArticle

Abstract

In this paper, a simple order filtering neural network, which can progressively output the value of a specific ordered input, is proposed. The progressive order filtering neural network (POFNN) is developed in a simple two-layer structure embedded with robustness. Both theoretical analyses and simulated results show that the designed order filtering neural network converges to the solution in logarithmic function of the dynamic range and the accuracy threshold, which are independent of the number of inputs.

Original languageEnglish
Pages (from-to)265-271
Number of pages7
JournalJournal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers,Series A/Chung-kuo Kung Ch'eng Hsuch K'an
Volume19
Issue number2
DOIs
Publication statusPublished - 1996 Jan 1

Fingerprint

Neural networks

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{ae5f19cf084442bd811a5ad5446b4f19,
title = "Order filtering neural network",
abstract = "In this paper, a simple order filtering neural network, which can progressively output the value of a specific ordered input, is proposed. The progressive order filtering neural network (POFNN) is developed in a simple two-layer structure embedded with robustness. Both theoretical analyses and simulated results show that the designed order filtering neural network converges to the solution in logarithmic function of the dynamic range and the accuracy threshold, which are independent of the number of inputs.",
author = "Chen, {Chi Ming} and Jar-Ferr Yang",
year = "1996",
month = "1",
day = "1",
doi = "10.1080/02533839.1996.9677786",
language = "English",
volume = "19",
pages = "265--271",
journal = "Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers",
issn = "0253-3839",
publisher = "Chinese Institute of Engineers",
number = "2",

}

TY - JOUR

T1 - Order filtering neural network

AU - Chen, Chi Ming

AU - Yang, Jar-Ferr

PY - 1996/1/1

Y1 - 1996/1/1

N2 - In this paper, a simple order filtering neural network, which can progressively output the value of a specific ordered input, is proposed. The progressive order filtering neural network (POFNN) is developed in a simple two-layer structure embedded with robustness. Both theoretical analyses and simulated results show that the designed order filtering neural network converges to the solution in logarithmic function of the dynamic range and the accuracy threshold, which are independent of the number of inputs.

AB - In this paper, a simple order filtering neural network, which can progressively output the value of a specific ordered input, is proposed. The progressive order filtering neural network (POFNN) is developed in a simple two-layer structure embedded with robustness. Both theoretical analyses and simulated results show that the designed order filtering neural network converges to the solution in logarithmic function of the dynamic range and the accuracy threshold, which are independent of the number of inputs.

UR - http://www.scopus.com/inward/record.url?scp=0030103798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030103798&partnerID=8YFLogxK

U2 - 10.1080/02533839.1996.9677786

DO - 10.1080/02533839.1996.9677786

M3 - Article

VL - 19

SP - 265

EP - 271

JO - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

JF - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

SN - 0253-3839

IS - 2

ER -