Cover Image

Improving generalization in backpropagation networks architectures

This paper gives a prototype recognizer that uses rough reduction module to find the optimal representation for backpropagation networks. The proposed approach exhibits a hybrid methodology for feedforward neural networks and rough set theory. The system is a two stand alone subsystems, in which the...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Adlan, Hanan Hassan, Ramli, Abd Rahman, Mohd Babiker, Elsadig Ahmed
Format: Conference or Workshop Item
Language:English
Published: 2005
Online Access:http://psasir.upm.edu.my/id/eprint/38992/1/38992.pdf
http://psasir.upm.edu.my/id/eprint/38992/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.38992
record_format eprints
spelling my.upm.eprints.389922015-07-13T07:14:49Z http://psasir.upm.edu.my/id/eprint/38992/ Improving generalization in backpropagation networks architectures Ali Adlan, Hanan Hassan Ramli, Abd Rahman Mohd Babiker, Elsadig Ahmed This paper gives a prototype recognizer that uses rough reduction module to find the optimal representation for backpropagation networks. The proposed approach exhibits a hybrid methodology for feedforward neural networks and rough set theory. The system is a two stand alone subsystems, in which the output of the first is fed to the second for recognition tasks. The system is investigated for detection and recognition of patterns present in an image. The rough module deals with uncertainty and irrelevant observations inherited in the data. The novel architecture integrates the two approaches to recognize pattern efficiently, with minimal neurons architecture. 2005 Conference or Workshop Item NonPeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/38992/1/38992.pdf Ali Adlan, Hanan Hassan and Ramli, Abd Rahman and Mohd Babiker, Elsadig Ahmed (2005) Improving generalization in backpropagation networks architectures. In: International Advanced Technology Congress: Conference on Intelligent Systems and Robotics, 6-8 Dec. 2005, Putrajaya, Malaysia. .
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description This paper gives a prototype recognizer that uses rough reduction module to find the optimal representation for backpropagation networks. The proposed approach exhibits a hybrid methodology for feedforward neural networks and rough set theory. The system is a two stand alone subsystems, in which the output of the first is fed to the second for recognition tasks. The system is investigated for detection and recognition of patterns present in an image. The rough module deals with uncertainty and irrelevant observations inherited in the data. The novel architecture integrates the two approaches to recognize pattern efficiently, with minimal neurons architecture.
format Conference or Workshop Item
author Ali Adlan, Hanan Hassan
Ramli, Abd Rahman
Mohd Babiker, Elsadig Ahmed
spellingShingle Ali Adlan, Hanan Hassan
Ramli, Abd Rahman
Mohd Babiker, Elsadig Ahmed
Improving generalization in backpropagation networks architectures
author_facet Ali Adlan, Hanan Hassan
Ramli, Abd Rahman
Mohd Babiker, Elsadig Ahmed
author_sort Ali Adlan, Hanan Hassan
title Improving generalization in backpropagation networks architectures
title_short Improving generalization in backpropagation networks architectures
title_full Improving generalization in backpropagation networks architectures
title_fullStr Improving generalization in backpropagation networks architectures
title_full_unstemmed Improving generalization in backpropagation networks architectures
title_sort improving generalization in backpropagation networks architectures
publishDate 2005
url http://psasir.upm.edu.my/id/eprint/38992/1/38992.pdf
http://psasir.upm.edu.my/id/eprint/38992/
_version_ 1643832293691752448
score 13.211869

Similar Items