Adaptive neural network classifier for extracted invariants of handwritten digits
We propose an adaptive activation function of neural network classifier for isolated handwritten digits that undergo basic transformations. The utilized network is a backpropagation network with sigmoid and arctangent activation functions. The performance of network with both activation functions is...
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Published: |
UUM PRESS, Universiti Utara Malaysia
2004
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/28194/ http://jict.uum.edu.my/index.php/previous-issues/131-journal-of-information-and-communication-technology-jict-vol-3-no-1-june-2004 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.28194 |
---|---|
record_format |
eprints |
spelling |
my.utm.281942018-11-30T07:07:17Z http://eprints.utm.my/id/eprint/28194/ Adaptive neural network classifier for extracted invariants of handwritten digits Keng, L. H. Shamsuddin, Siti Mariyam QA75 Electronic computers. Computer science We propose an adaptive activation function of neural network classifier for isolated handwritten digits that undergo basic transformations. The utilized network is a backpropagation network with sigmoid and arctangent activation functions. The performance of network with both activation functions is compared. The results show that the network applying an adaptive activation function between layers converged much faster compared to non-adaptive activation functions with 50% iterations reduction. In this study, we also present experimental results of feature extraction between Zernike and d-geometric for better feature representations. Results show that Zernike features are better at representing isolated handwritten digits compared to d-geometric features with an accuracy up to 87%. UUM PRESS, Universiti Utara Malaysia 2004-06 Article PeerReviewed Keng, L. H. and Shamsuddin, Siti Mariyam (2004) Adaptive neural network classifier for extracted invariants of handwritten digits. Journal of Information and Communication Technology (JICT), 3 (1). pp. 1-17. ISSN 2180-3862 http://jict.uum.edu.my/index.php/previous-issues/131-journal-of-information-and-communication-technology-jict-vol-3-no-1-june-2004 |
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/ |
topic |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Keng, L. H. Shamsuddin, Siti Mariyam Adaptive neural network classifier for extracted invariants of handwritten digits |
description |
We propose an adaptive activation function of neural network classifier for isolated handwritten digits that undergo basic transformations. The utilized network is a backpropagation network with sigmoid and arctangent activation functions. The performance of network with both activation functions is compared. The results show that the network applying an adaptive activation function between layers converged much faster compared to non-adaptive activation functions with 50% iterations reduction. In this study, we also present experimental results of feature extraction between Zernike and d-geometric for better feature representations. Results show that Zernike features are better at representing isolated handwritten digits compared to d-geometric features with an accuracy up to 87%. |
format |
Article |
author |
Keng, L. H. Shamsuddin, Siti Mariyam |
author_facet |
Keng, L. H. Shamsuddin, Siti Mariyam |
author_sort |
Keng, L. H. |
title |
Adaptive neural network classifier for extracted invariants of handwritten digits |
title_short |
Adaptive neural network classifier for extracted invariants of handwritten digits |
title_full |
Adaptive neural network classifier for extracted invariants of handwritten digits |
title_fullStr |
Adaptive neural network classifier for extracted invariants of handwritten digits |
title_full_unstemmed |
Adaptive neural network classifier for extracted invariants of handwritten digits |
title_sort |
adaptive neural network classifier for extracted invariants of handwritten digits |
publisher |
UUM PRESS, Universiti Utara Malaysia |
publishDate |
2004 |
url |
http://eprints.utm.my/id/eprint/28194/ http://jict.uum.edu.my/index.php/previous-issues/131-journal-of-information-and-communication-technology-jict-vol-3-no-1-june-2004 |
_version_ |
1643648004428660736 |
score |
13.160551 |