Feedforward backpropagation artificial neural networks on reconfigurable meshes

John Jing Fu Jenq; Wingning Li

doi:10.1016/s0167-739x(98)00036-3

Feedforward backpropagation artificial neural networks on reconfigurable meshes

John Jing Fu Jenq, Wingning Li

Computer Science

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

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 language	English
Pages (from-to)	313-319
Number of pages	7
Journal	Future Generation Computer Systems
Volume	14
Issue number	5-6
DOIs	https://doi.org/10.1016/s0167-739x(98)00036-3
State	Published - Dec 1998

Keywords

Artificial neural networks
Parallel algorithms
Reconfigurable mesh algorithms

Access to Document

10.1016/s0167-739x(98)00036-3

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 = "Jenq, {John Jing Fu} and Wingning Li",

year = "1998",

month = dec,

doi = "10.1016/s0167-739x(98)00036-3",

language = "English",

volume = "14",

pages = "313--319",

journal = "Future Generation Computer Systems",

issn = "0167-739X",

publisher = "Elsevier B.V.",

number = "5-6",

}

TY - JOUR

T1 - Feedforward backpropagation artificial neural networks on reconfigurable meshes

AU - Jenq, John Jing Fu

AU - Li, Wingning

PY - 1998/12

Y1 - 1998/12

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

U2 - 10.1016/s0167-739x(98)00036-3

DO - 10.1016/s0167-739x(98)00036-3

M3 - Article

AN - SCOPUS:0032317735

SN - 0167-739X

VL - 14

SP - 313

EP - 319

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

IS - 5-6

ER -

Feedforward backpropagation artificial neural networks on reconfigurable meshes

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this