True parallel processing in artificial neural networks

True parallel processing in artificial neural networks

The area of artificial neural networks, which dates back to the early twentieth century, could only offer positive contributions to technology after the back-propagation algorithm was proposed in 1986. In this note an alternative algorithm to the gradient descent used in back-propagation is proposed...

Full description

Saved in:
Bibliographic Details
Published in:Kybernetes Vol. 30; no. 9/10; pp. 1192 - 1198
Main Author: Engel, Alejandro B
Format: Journal Article
Language:English
Published: London MCB UP Ltd 01-12-2001
Emerald Group Publishing Limited
Subjects:
Algorithms
Cybernetics
Neural networks
Parallel computing
Parallel processing
Parallel computing
Algorithms
Neural networks
Cybernetics
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The area of artificial neural networks, which dates back to the early twentieth century, could only offer positive contributions to technology after the back-propagation algorithm was proposed in 1986. In this note an alternative algorithm to the gradient descent used in back-propagation is proposed. This algorithm is based on the discrete central difference. This procedure, as opposed to the back-propagation algorithm, offers the possibility of true parallel computation.
Bibliography:filenameID:0670300915
ark:/67375/4W2-4DKMXQKH-9
istex:DC18BF5D797B7580020B5D1B1FC852802A0F785D
original-pdf:0670300915.pdf
href:03684920110405764.pdf
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0368-492X
1758-7883
DOI:10.1108/03684920110405764