Feedforward backpropagation artificial neural networks on reconfigurable meshes

John Jenq, Wingning Li

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Abstract

The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applications use backpropagate feedforward ANN. In this paper, two methods of P pattern L layer ANN learning on n × n RMESH have been presented. One required memory space of O(nL) but conceptually is simpler to develop and the other uses pipelined approach which reduces the memory requirement to O(L). Both of these algorithms take O(PL) time and are optimal for RMESH architecture.

Original languageEnglish
Pages (from-to)313-319
Number of pages7
JournalFuture Generation Computer Systems
Volume14
Issue number5-6
StatePublished - 1 Dec 1998

Fingerprint

Backpropagation
Neural networks
Data storage equipment
Pattern recognition
Image processing
Automation

Keywords

  • Artificial neural networks
  • Parallel algorithms
  • Reconfigurable mesh algorithms

Cite this

@article{d5519e640dd24c74a70e998f735bbc29,
title = "Feedforward backpropagation artificial neural networks on reconfigurable meshes",
abstract = "The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applications use backpropagate feedforward ANN. In this paper, two methods of P pattern L layer ANN learning on n × n RMESH have been presented. One required memory space of O(nL) but conceptually is simpler to develop and the other uses pipelined approach which reduces the memory requirement to O(L). Both of these algorithms take O(PL) time and are optimal for RMESH architecture.",
keywords = "Artificial neural networks, Parallel algorithms, Reconfigurable mesh algorithms",
author = "John Jenq and Wingning Li",
year = "1998",
month = "12",
day = "1",
language = "English",
volume = "14",
pages = "313--319",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",
number = "5-6",

}

Feedforward backpropagation artificial neural networks on reconfigurable meshes. / Jenq, John; Li, Wingning.

In: Future Generation Computer Systems, Vol. 14, No. 5-6, 01.12.1998, p. 313-319.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Feedforward backpropagation artificial neural networks on reconfigurable meshes

AU - Jenq, John

AU - Li, Wingning

PY - 1998/12/1

Y1 - 1998/12/1

N2 - The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applications use backpropagate feedforward ANN. In this paper, two methods of P pattern L layer ANN learning on n × n RMESH have been presented. One required memory space of O(nL) but conceptually is simpler to develop and the other uses pipelined approach which reduces the memory requirement to O(L). Both of these algorithms take O(PL) time and are optimal for RMESH architecture.

AB - The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applications use backpropagate feedforward ANN. In this paper, two methods of P pattern L layer ANN learning on n × n RMESH have been presented. One required memory space of O(nL) but conceptually is simpler to develop and the other uses pipelined approach which reduces the memory requirement to O(L). Both of these algorithms take O(PL) time and are optimal for RMESH architecture.

KW - Artificial neural networks

KW - Parallel algorithms

KW - Reconfigurable mesh algorithms

UR - http://www.scopus.com/inward/record.url?scp=0032317735&partnerID=8YFLogxK

M3 - Article

VL - 14

SP - 313

EP - 319

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

IS - 5-6

ER -