Extended backpropagation algorithm

Y. F. Yam; T. W S Chow

Extended backpropagation algorithm

Y. F. Yam
, T. W S Chow

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

Abstract

A fast learning algorithm for feedforward neural networks is described. This algorithm is based on modification to the back-propagation algorithm. The learning rate and momentum coefficient are adapted according to the coefficient of correlation between the downhill gradient and the previous weight update.

Original language	English
Pages (from-to)	1701-1702
Journal	Electronics Letters
Volume	29
Issue number	19
Publication status	Published - 1 Jan 1993
Externally published	Yes

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{3f13f81cbb7d4d6f9b07c4a198c4bb79,

title = "Extended backpropagation algorithm",

abstract = "A fast learning algorithm for feedforward neural networks is described. This algorithm is based on modification to the back-propagation algorithm. The learning rate and momentum coefficient are adapted according to the coefficient of correlation between the downhill gradient and the previous weight update.",

author = "Yam, \{Y. F.\} and Chow, \{T. W S\}",

year = "1993",

month = jan,

day = "1",

language = "English",

volume = "29",

pages = "1701--1702",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley \& Sons",

number = "19",

}

TY - JOUR

T1 - Extended backpropagation algorithm

AU - Yam, Y. F.

AU - Chow, T. W S

PY - 1993/1/1

Y1 - 1993/1/1

N2 - A fast learning algorithm for feedforward neural networks is described. This algorithm is based on modification to the back-propagation algorithm. The learning rate and momentum coefficient are adapted according to the coefficient of correlation between the downhill gradient and the previous weight update.

AB - A fast learning algorithm for feedforward neural networks is described. This algorithm is based on modification to the back-propagation algorithm. The learning rate and momentum coefficient are adapted according to the coefficient of correlation between the downhill gradient and the previous weight update.

UR - https://www.scopus.com/pages/publications/0027668649

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0027668649&origin=recordpage

M3 - RGC 21 - Publication in refereed journal

SN - 0013-5194

VL - 29

SP - 1701

EP - 1702

JO - Electronics Letters

JF - Electronics Letters

IS - 19

ER -

Extended backpropagation algorithm

Abstract

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this