Progressive and constant-speed order filtering neural network

Chi Ming Chen, Jar-Ferr Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a new order filtering neural network, which can select a specific ordered value from all inputs, is developed and analyzed. The proposed neural net in two-layer structure iteratively converges to the solution with low and constant convergent speed, which is independent of the number of inputs. With progressive behavior, the proposed neural net obtains the more accurate result when the number of iterations increases if the derived convergent condition is satisfied. From the view points of convergence speed and hardware complexity, the proposed order filtering neural network is suitable for various applications.

Original languageEnglish
Title of host publicationIEEE Asia-Pacific Conference on Circuits and Systems - Proceedings
PublisherIEEE
Pages13-17
Number of pages5
Publication statusPublished - 1994
EventProceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems - Taipei, Taiwan
Duration: 1994 Dec 51994 Dec 8

Other

OtherProceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems
CityTaipei, Taiwan
Period94-12-0594-12-08

Fingerprint

Neural networks
Hardware

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Chen, C. M., & Yang, J-F. (1994). Progressive and constant-speed order filtering neural network. In IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings (pp. 13-17). IEEE.
Chen, Chi Ming ; Yang, Jar-Ferr. / Progressive and constant-speed order filtering neural network. IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings. IEEE, 1994. pp. 13-17
@inproceedings{d8e6dbc0026a4153be1cfc2255c3523f,
title = "Progressive and constant-speed order filtering neural network",
abstract = "In this paper, a new order filtering neural network, which can select a specific ordered value from all inputs, is developed and analyzed. The proposed neural net in two-layer structure iteratively converges to the solution with low and constant convergent speed, which is independent of the number of inputs. With progressive behavior, the proposed neural net obtains the more accurate result when the number of iterations increases if the derived convergent condition is satisfied. From the view points of convergence speed and hardware complexity, the proposed order filtering neural network is suitable for various applications.",
author = "Chen, {Chi Ming} and Jar-Ferr Yang",
year = "1994",
language = "English",
pages = "13--17",
booktitle = "IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings",
publisher = "IEEE",

}

Chen, CM & Yang, J-F 1994, Progressive and constant-speed order filtering neural network. in IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings. IEEE, pp. 13-17, Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems, Taipei, Taiwan, 94-12-05.

Progressive and constant-speed order filtering neural network. / Chen, Chi Ming; Yang, Jar-Ferr.

IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings. IEEE, 1994. p. 13-17.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Progressive and constant-speed order filtering neural network

AU - Chen, Chi Ming

AU - Yang, Jar-Ferr

PY - 1994

Y1 - 1994

N2 - In this paper, a new order filtering neural network, which can select a specific ordered value from all inputs, is developed and analyzed. The proposed neural net in two-layer structure iteratively converges to the solution with low and constant convergent speed, which is independent of the number of inputs. With progressive behavior, the proposed neural net obtains the more accurate result when the number of iterations increases if the derived convergent condition is satisfied. From the view points of convergence speed and hardware complexity, the proposed order filtering neural network is suitable for various applications.

AB - In this paper, a new order filtering neural network, which can select a specific ordered value from all inputs, is developed and analyzed. The proposed neural net in two-layer structure iteratively converges to the solution with low and constant convergent speed, which is independent of the number of inputs. With progressive behavior, the proposed neural net obtains the more accurate result when the number of iterations increases if the derived convergent condition is satisfied. From the view points of convergence speed and hardware complexity, the proposed order filtering neural network is suitable for various applications.

UR - http://www.scopus.com/inward/record.url?scp=0028731622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028731622&partnerID=8YFLogxK

M3 - Conference contribution

SP - 13

EP - 17

BT - IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings

PB - IEEE

ER -

Chen CM, Yang J-F. Progressive and constant-speed order filtering neural network. In IEEE Asia-Pacific Conference on Circuits and Systems - Proceedings. IEEE. 1994. p. 13-17