Improving generalization in backpropagation networks architectures

Citation

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. .

Abstract

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.

Download File

PDF (Full text)
38992.pdf - Published Version
Restricted to Repository staff only
Download (147kB)

Additional Metadata

Item Type:	Conference or Workshop Item (Paper)
Divisions:	Faculty of Engineering
Keywords:	Pattern recognition; Hybrid modeling; Neural networks; Rough set theory
Depositing User:	Erni Suraya Abdul Aziz
Date Deposited:	13 Jul 2015 07:14
Last Modified:	13 Jul 2015 07:14
URI:	http://psasir.upm.edu.my/id/eprint/38992
Statistic Details:	View Download Statistic

Actions (login required)

View Item