A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition

This paper presents an investigation that aims at comparing deep learning (DL) and traditional artificial neural networks (ANNs) in the application of hand-written digits recognition (HDR). In our study, convolution neural networks (CNNs) are a representative model for the DL models and the multi-la...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Rababaah, Aaron (author)
منشور في: 2023
الوصول للمادة أونلاين:http://hdl.handle.net/11675/10928
https://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=ijcvr
http://www.scopus.com/inward/record.url?scp=85166402843&partnerID=8YFLogxK
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1870679718107283457
author Rababaah, Aaron
author_facet Rababaah, Aaron
author_role author
dc.creator.none.fl_str_mv Rababaah, Aaron
dc.date.none.fl_str_mv 2023-01-01
2024-02-05T08:32:41Z
2024-02-05T08:32:41Z
dc.identifier.none.fl_str_mv 10.1504/IJCVR.2023.131985
http://hdl.handle.net/11675/10928
https://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=ijcvr
http://www.scopus.com/inward/record.url?scp=85166402843&partnerID=8YFLogxK
dc.publisher.none.fl_str_mv Inderscience Enterprises Ltd
dc.relation.none.fl_str_mv Computer Science and Info Systems
International Journal of Computational Vision and Robotics
dc.title.none.fl_str_mv A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
dc.type.none.fl_str_mv Other
info:eu-repo/semantics/publishedVersion
description This paper presents an investigation that aims at comparing deep learning (DL) and traditional artificial neural networks (ANNs) in the application of hand-written digits recognition (HDR). In our study, convolution neural networks (CNNs) are a representative model for the DL models and the multi-layer perceptron (MLP) is a representative model for ANN models. The two models MLP and CNN were implemented using MATLAB development environment and tested using a publicly available image database. The databse consists of over 20,000 samples with all ten hand-written digits each of which is 24 × 24 pixels. The experimental results showed that the CNN model was superior to the MLP model with an average classification accuracy of 95.14% and 89.74% respectively. Furthermore, the CNN model was observed to have better performance stability and better execution efficiency as the MLP model requires human intervention to handcraft and pre-process the features of the digit patterns.
id AUKR_0e4eb90b8dd2c84c10b2abcd3ec49e3d
identifier_str_mv 10.1504/IJCVR.2023.131985
network_acronym_str AUKR
network_name_str AU Kuwait Rep
oai_identifier_str oai:dspace.auk.edu.kw:11675/10928
publishDate 2023
publisher.none.fl_str_mv Inderscience Enterprises Ltd
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognitionRababaah, AaronThis paper presents an investigation that aims at comparing deep learning (DL) and traditional artificial neural networks (ANNs) in the application of hand-written digits recognition (HDR). In our study, convolution neural networks (CNNs) are a representative model for the DL models and the multi-layer perceptron (MLP) is a representative model for ANN models. The two models MLP and CNN were implemented using MATLAB development environment and tested using a publicly available image database. The databse consists of over 20,000 samples with all ten hand-written digits each of which is 24 × 24 pixels. The experimental results showed that the CNN model was superior to the MLP model with an average classification accuracy of 95.14% and 89.74% respectively. Furthermore, the CNN model was observed to have better performance stability and better execution efficiency as the MLP model requires human intervention to handcraft and pre-process the features of the digit patterns.Inderscience Enterprises Ltd2024-02-05T08:32:41Z2024-02-05T08:32:41Z2023-01-01Otherinfo:eu-repo/semantics/publishedVersion10.1504/IJCVR.2023.131985http://hdl.handle.net/11675/10928https://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=ijcvrhttp://www.scopus.com/inward/record.url?scp=85166402843&partnerID=8YFLogxKComputer Science and Info SystemsInternational Journal of Computational Vision and Roboticsoai:dspace.auk.edu.kw:11675/109282025-06-18T08:58:37Z
spellingShingle A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
Rababaah, Aaron
status_str publishedVersion
title A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
title_full A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
title_fullStr A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
title_full_unstemmed A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
title_short A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
title_sort A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
url http://hdl.handle.net/11675/10928
https://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=ijcvr
http://www.scopus.com/inward/record.url?scp=85166402843&partnerID=8YFLogxK