Effect of Learning Rate on the Recognition of Images

This paper presents a study for the effect of learning rate on an approach for texture classification and detection based on the neural network principle. This neural network consists of three layers, which are input, output, and hidden layers. The back propagation technique is considered. A compute...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Hamed, A. El Desouky
Format: Article
Language:English
Published: Wiley 1996-01-01
Series:Active and Passive Electronic Components
Subjects:
Online Access:http://dx.doi.org/10.1155/1996/45086
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832567172810932224
author M. Hamed
A. El Desouky
author_facet M. Hamed
A. El Desouky
author_sort M. Hamed
collection DOAJ
description This paper presents a study for the effect of learning rate on an approach for texture classification and detection based on the neural network principle. This neural network consists of three layers, which are input, output, and hidden layers. The back propagation technique is considered. A computer algorithm is deduced and applied. In this work, the synthetic textures are generated. The results are taken for the modern computer of AT 486 type. The mathematical analysis is summarized in order to illustrate the effect of learning rate parameter on the exact discrimination during processing. This effect is studied through applications. The minimum consumed time for the computational time of classification in industry is correlated to correspond only the use of only 2 units in the hidden layer of a neural network for real images instead of 11 units.
format Article
id doaj-art-65edd6a8774c4a749b4e940d5c0e8c80
institution Kabale University
issn 0882-7516
1563-5031
language English
publishDate 1996-01-01
publisher Wiley
record_format Article
series Active and Passive Electronic Components
spelling doaj-art-65edd6a8774c4a749b4e940d5c0e8c802025-02-03T01:02:11ZengWileyActive and Passive Electronic Components0882-75161563-50311996-01-0119111210.1155/1996/45086Effect of Learning Rate on the Recognition of ImagesM. Hamed0A. El Desouky1Faculty of Engineering, Suez Canal University, Port Said, EgyptFaculty of Engineering, Suez Canal University, Port Said, EgyptThis paper presents a study for the effect of learning rate on an approach for texture classification and detection based on the neural network principle. This neural network consists of three layers, which are input, output, and hidden layers. The back propagation technique is considered. A computer algorithm is deduced and applied. In this work, the synthetic textures are generated. The results are taken for the modern computer of AT 486 type. The mathematical analysis is summarized in order to illustrate the effect of learning rate parameter on the exact discrimination during processing. This effect is studied through applications. The minimum consumed time for the computational time of classification in industry is correlated to correspond only the use of only 2 units in the hidden layer of a neural network for real images instead of 11 units.http://dx.doi.org/10.1155/1996/45086neuralcomputertextureclassificationdiscriminationWalshvision systempattern recognitiondata reductiontrainingtesthidden.
spellingShingle M. Hamed
A. El Desouky
Effect of Learning Rate on the Recognition of Images
Active and Passive Electronic Components
neural
computer
texture
classification
discrimination
Walsh
vision system
pattern recognition
data reduction
training
test
hidden.
title Effect of Learning Rate on the Recognition of Images
title_full Effect of Learning Rate on the Recognition of Images
title_fullStr Effect of Learning Rate on the Recognition of Images
title_full_unstemmed Effect of Learning Rate on the Recognition of Images
title_short Effect of Learning Rate on the Recognition of Images
title_sort effect of learning rate on the recognition of images
topic neural
computer
texture
classification
discrimination
Walsh
vision system
pattern recognition
data reduction
training
test
hidden.
url http://dx.doi.org/10.1155/1996/45086
work_keys_str_mv AT mhamed effectoflearningrateontherecognitionofimages
AT aeldesouky effectoflearningrateontherecognitionofimages