Back propagation with expected source values

Tariq Samad

doi:10.1016/0893-6080(91)90015-W

Back propagation with expected source values

Tariq Samad

Technological Leadership Institute

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

21 Scopus citations

Abstract

The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.

Original language	English (US)
Pages (from-to)	615-618
Number of pages	4
Journal	Neural Networks
Volume	4
Issue number	5
DOIs	https://doi.org/10.1016/0893-6080(91)90015-W
State	Published - 1991

Bibliographical note

Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.

Keywords

Back propagation
Neural networks
Supervised learning

Access

10.1016/0893-6080(91)90015-W

OpenUrl availability

Full text

Cite this

@article{b3ead4faa1524e219bf38932ecf12acf,

title = "Back propagation with expected source values",

abstract = "The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.",

keywords = "Back propagation, Neural networks, Supervised learning",

author = "Tariq Samad",

year = "1991",

doi = "10.1016/0893-6080(91)90015-W",

language = "English (US)",

volume = "4",

pages = "615--618",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "5",

}

TY - JOUR

T1 - Back propagation with expected source values

AU - Samad, Tariq

PY - 1991

Y1 - 1991

N2 - The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.

AB - The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.

KW - Back propagation

KW - Neural networks

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=0025750495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025750495&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(91)90015-W

DO - 10.1016/0893-6080(91)90015-W

M3 - Article

AN - SCOPUS:0025750495

SN - 0893-6080

VL - 4

SP - 615

EP - 618

JO - Neural Networks

JF - Neural Networks

IS - 5

ER -

Back propagation with expected source values

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this