Universiti Teknologi Malaysia Institutional Repository

A performances study of enhanced bp algorithms on aircraft image classification

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

[img]
Preview
PDF
65Kb

Abstract

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.

Item Type:Book Section
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:16256
Deposited By: Liza Porijo
Deposited On:21 Oct 2011 09:32
Last Modified:21 Oct 2011 09:32

Repository Staff Only: item control page