Cover Image

A framework for multiprocessor neural networks systems

Artificial neural networks (ANN) are able to simplify classification tasks and have been steadily improving both in accuracy and efficiency. However, there are several issues that need to be addressed when constructing an ANN for handling different scales of data, especially those with a low accurac...

Full description

Saved in:
Bibliographic Details
Main Author: Mumtazimah, Mohamad
Format: Conference or Workshop Item
Language:English
Published: 2012
Subjects:
Q Science (General)
T Technology (General)
Online Access:http://eprints.unisza.edu.my/134/1/FH03-FIK-16-05752.jpg
http://eprints.unisza.edu.my/134/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-unisza-ir.134
record_format eprints
spelling my-unisza-ir.1342020-10-19T05:09:41Z http://eprints.unisza.edu.my/134/ A framework for multiprocessor neural networks systems Mumtazimah, Mohamad Q Science (General) T Technology (General) Artificial neural networks (ANN) are able to simplify classification tasks and have been steadily improving both in accuracy and efficiency. However, there are several issues that need to be addressed when constructing an ANN for handling different scales of data, especially those with a low accuracy score. Parallelism is considered as a practical solution to solve a large workload. However, a comprehensive understanding is needed to generate a scalable neural network that is able to achieve the optimal training time for a large network. Therefore, this paper proposes several strategies, including neural ensemble techniques and parallel architecture, for distributing data to several network processor structures to reduce the time required for recognition tasks without compromising the achieved accuracy. The initial results indicate that the proposed strategies are able to improve the speed up performance for large scale neural networks while maintaining an acceptable accuracy. 2012 Conference or Workshop Item PeerReviewed image en http://eprints.unisza.edu.my/134/1/FH03-FIK-16-05752.jpg Mumtazimah, Mohamad (2012) A framework for multiprocessor neural networks systems. In: International Conference on ICT Convergence: "Global Open Innovation Summit for Smart ICT Convergence", 15-17 October 2012, Jeju Island; South Korea.
institution Universiti Sultan Zainal Abidin
building UNISZA Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Sultan Zainal Abidin
content_source UNISZA Institutional Repository
url_provider https://eprints.unisza.edu.my/
language English
topic Q Science (General)
T Technology (General)
spellingShingle Q Science (General)
T Technology (General)
Mumtazimah, Mohamad
A framework for multiprocessor neural networks systems
description Artificial neural networks (ANN) are able to simplify classification tasks and have been steadily improving both in accuracy and efficiency. However, there are several issues that need to be addressed when constructing an ANN for handling different scales of data, especially those with a low accuracy score. Parallelism is considered as a practical solution to solve a large workload. However, a comprehensive understanding is needed to generate a scalable neural network that is able to achieve the optimal training time for a large network. Therefore, this paper proposes several strategies, including neural ensemble techniques and parallel architecture, for distributing data to several network processor structures to reduce the time required for recognition tasks without compromising the achieved accuracy. The initial results indicate that the proposed strategies are able to improve the speed up performance for large scale neural networks while maintaining an acceptable accuracy.
format Conference or Workshop Item
author Mumtazimah, Mohamad
author_facet Mumtazimah, Mohamad
author_sort Mumtazimah, Mohamad
title A framework for multiprocessor neural networks systems
title_short A framework for multiprocessor neural networks systems
title_full A framework for multiprocessor neural networks systems
title_fullStr A framework for multiprocessor neural networks systems
title_full_unstemmed A framework for multiprocessor neural networks systems
title_sort framework for multiprocessor neural networks systems
publishDate 2012
url http://eprints.unisza.edu.my/134/1/FH03-FIK-16-05752.jpg
http://eprints.unisza.edu.my/134/
_version_ 1681493192844771328
score 13.211869

Similar Items