Cover Image

A performances study of enhanced bp algorithms on aircraft image classification

BP is by far the most widely used algorithm to train MLPs for pattern recognition and other similar tasks. However it is stigmatized with the problems of low convergence, instability and overfitting. In addition, the optimal values of the learning rate, momentum, the number of hidden layers an...

Full description

Saved in:
Bibliographic Details
Main Authors: Saad, Puteh, Mahsos, Nursafawati, Ibrahim, Subariah, Darius, Rusni
Format: Book Section
Language:English
Published: Penerbit UTM 2008
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/id/eprint/16256/1/A_performances_study_of_enhanced_bp_algorithms_on_aircraft_image_classification.pdf
http://eprints.utm.my/id/eprint/16256/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.16256
record_format eprints
spelling my.utm.162562011-10-21T09:32:45Z http://eprints.utm.my/id/eprint/16256/ A performances study of enhanced bp algorithms on aircraft image classification Saad, Puteh Mahsos, Nursafawati Ibrahim, Subariah Darius, Rusni QA75 Electronic computers. Computer science BP is by far the most widely used algorithm to train MLPs for pattern recognition and other similar tasks. However it is stigmatized with the problems of low convergence, instability and overfitting. In addition, the optimal values of the learning rate, momentum, the number of hidden layers and its dimension are obtained through trial and error method. In this work, we evaluate eleven (11) enhanced BP algorithms in classifying aircraft images. The image is represented using a set of Zernike Moment Invariants. Penerbit UTM 2008 Book Section PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/16256/1/A_performances_study_of_enhanced_bp_algorithms_on_aircraft_image_classification.pdf Saad, Puteh and Mahsos, Nursafawati and Ibrahim, Subariah and Darius, Rusni (2008) A performances study of enhanced bp algorithms on aircraft image classification. In: Advances in Artificial Intelligence Applications. Penerbit UTM , Johor, pp. 36-62. ISBN 978-983-52-0623-8
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Saad, Puteh
Mahsos, Nursafawati
Ibrahim, Subariah
Darius, Rusni
A performances study of enhanced bp algorithms on aircraft image classification
description BP is by far the most widely used algorithm to train MLPs for pattern recognition and other similar tasks. However it is stigmatized with the problems of low convergence, instability and overfitting. In addition, the optimal values of the learning rate, momentum, the number of hidden layers and its dimension are obtained through trial and error method. In this work, we evaluate eleven (11) enhanced BP algorithms in classifying aircraft images. The image is represented using a set of Zernike Moment Invariants.
format Book Section
author Saad, Puteh
Mahsos, Nursafawati
Ibrahim, Subariah
Darius, Rusni
author_facet Saad, Puteh
Mahsos, Nursafawati
Ibrahim, Subariah
Darius, Rusni
author_sort Saad, Puteh
title A performances study of enhanced bp algorithms on aircraft image classification
title_short A performances study of enhanced bp algorithms on aircraft image classification
title_full A performances study of enhanced bp algorithms on aircraft image classification
title_fullStr A performances study of enhanced bp algorithms on aircraft image classification
title_full_unstemmed A performances study of enhanced bp algorithms on aircraft image classification
title_sort performances study of enhanced bp algorithms on aircraft image classification
publisher Penerbit UTM
publishDate 2008
url http://eprints.utm.my/id/eprint/16256/1/A_performances_study_of_enhanced_bp_algorithms_on_aircraft_image_classification.pdf
http://eprints.utm.my/id/eprint/16256/
_version_ 1643646508480856064
score 13.18916

Similar Items