Case study : an effect of noise in character recognition system using neural network

There has been resurgence of interest in artificial neural networks over the past few years, as a researchers from diverse backgrounds have produced a firms theoretical foundation and demonstrated numerous applications of this rich field of study. Neural networks are useful tools for solving many...

Full description

Saved in:
Bibliographic Details
Main Author: Mohamad, Esmawaty
Format: Thesis
Language:English
English
Published: 2003
Subjects:
Online Access:http://psasir.upm.edu.my/id/eprint/8706/1/FSKTM_2003_8%20IR.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-upm-ir.8706
record_format uketd_dc
spelling my-upm-ir.87062023-12-28T01:21:21Z Case study : an effect of noise in character recognition system using neural network 2003-05 Mohamad, Esmawaty There has been resurgence of interest in artificial neural networks over the past few years, as a researchers from diverse backgrounds have produced a firms theoretical foundation and demonstrated numerous applications of this rich field of study. Neural networks are useful tools for solving many type of problems. These problems may be characterized as mapping(including pattern association and pattern classification), clustering and constrained optimization. There has been great deal of work on enhancing neural network performance. Two important parameter are convergence and generalization. Convergence is the amount of time, measured in CPU operations or training epochs, required to find an acceptable solution for training. Generalization measures the ability to correctly classify new unseen data. This project studies the generalization ability of trained network to classify noisy data. The aim of this project is to develop a network that is able to recognize various inputs through a series of simulation using Neural Network simulator called MATLAB. The effect of the created network with noise are seen. This projects uses the most popular training method in character recognition problem, namely backpropagation algorithm. The theoretical foundation of this algorithm will be studied and summarized. Simulation experiment results on training and testing data will be recorded and discussed. Neural networks (Computer science) - Case studies Noise - Case studies 2003-05 Thesis http://psasir.upm.edu.my/id/eprint/8706/ http://psasir.upm.edu.my/id/eprint/8706/1/FSKTM_2003_8%20IR.pdf text en public masters Universiti Putra Malaysia Neural networks (Computer science) - Case studies Noise - Case studies Faculty of Computer Science and Information Technology Mohd Aris, Teh Noranis English
institution Universiti Putra Malaysia
collection PSAS Institutional Repository
language English
English
advisor Mohd Aris, Teh Noranis
topic Neural networks (Computer science) - Case studies
Noise - Case studies

spellingShingle Neural networks (Computer science) - Case studies
Noise - Case studies

Mohamad, Esmawaty
Case study : an effect of noise in character recognition system using neural network
description There has been resurgence of interest in artificial neural networks over the past few years, as a researchers from diverse backgrounds have produced a firms theoretical foundation and demonstrated numerous applications of this rich field of study. Neural networks are useful tools for solving many type of problems. These problems may be characterized as mapping(including pattern association and pattern classification), clustering and constrained optimization. There has been great deal of work on enhancing neural network performance. Two important parameter are convergence and generalization. Convergence is the amount of time, measured in CPU operations or training epochs, required to find an acceptable solution for training. Generalization measures the ability to correctly classify new unseen data. This project studies the generalization ability of trained network to classify noisy data. The aim of this project is to develop a network that is able to recognize various inputs through a series of simulation using Neural Network simulator called MATLAB. The effect of the created network with noise are seen. This projects uses the most popular training method in character recognition problem, namely backpropagation algorithm. The theoretical foundation of this algorithm will be studied and summarized. Simulation experiment results on training and testing data will be recorded and discussed.
format Thesis
qualification_level Master's degree
author Mohamad, Esmawaty
author_facet Mohamad, Esmawaty
author_sort Mohamad, Esmawaty
title Case study : an effect of noise in character recognition system using neural network
title_short Case study : an effect of noise in character recognition system using neural network
title_full Case study : an effect of noise in character recognition system using neural network
title_fullStr Case study : an effect of noise in character recognition system using neural network
title_full_unstemmed Case study : an effect of noise in character recognition system using neural network
title_sort case study : an effect of noise in character recognition system using neural network
granting_institution Universiti Putra Malaysia
granting_department Faculty of Computer Science and Information Technology
publishDate 2003
url http://psasir.upm.edu.my/id/eprint/8706/1/FSKTM_2003_8%20IR.pdf
_version_ 1794018774683222016