Cover Image

Training process reduction based on potential weights linear analysis to accelerate back propagation network.

Learning is the important property of Back Propagation Network (BPN) and finding the suitable weights and thresholds during training in order to improve training time as well as achieve high accuracy. Currently, data pre-processing such as dimension reduction input values and pre-training are the c...

Full description

Saved in:
Bibliographic Details
Main Authors: Asadi, Roya, Mustapha, Norwati, Sulaiman, Md. Nasir
Format: Article
Language:English
English
Published: IJCSIS Press 2009
Online Access:http://psasir.upm.edu.my/id/eprint/17465/1/Training%20process%20reduction%20based%20on%20potential%20weights%20linear%20analysis%20to%20accelerate%20back%20propagation%20network.pdf
http://psasir.upm.edu.my/id/eprint/17465/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.17465
record_format eprints
spelling my.upm.eprints.174652015-11-16T01:17:45Z http://psasir.upm.edu.my/id/eprint/17465/ Training process reduction based on potential weights linear analysis to accelerate back propagation network. Asadi, Roya Mustapha, Norwati Sulaiman, Md. Nasir Learning is the important property of Back Propagation Network (BPN) and finding the suitable weights and thresholds during training in order to improve training time as well as achieve high accuracy. Currently, data pre-processing such as dimension reduction input values and pre-training are the contributing factors in developing efficient techniques for reducing training time with high accuracy and initialization of the weights is the important issue which is random and creates paradox, and leads to low accuracy with high training time. One good data preprocessing technique for accelerating BPN classification is dimension reduction technique but it has problem of missing data. In this paper, we study current pre-training techniques and new preprocessing technique called Potential Weight Linear Analysis (PWLA) which combines normalization, dimension reduction input values and pre-training. In PWLA, the first data preprocessing is performed for generating normalized input values and then applying them by pre-training technique in order to obtain the potential weights. After these phases, dimension of input values matrix will be reduced by using real potential weights. For experiment results XOR problem and three datasets, which are SPECT Heart, SPECTF Heart and Liver disorders (BUPA) will be evaluated. Our results, however, will show that the new technique of PWLA will change BPN to new Supervised Multi Layer Feed Forward Neural Network (SMFFNN) model with high accuracy in one epoch without training cycle. Also PWLA will be able to have power of non linear supervised and unsupervised dimension reduction property for applying by other supervised multi layer feed forward neural network model in future work. IJCSIS Press 2009-07 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/17465/1/Training%20process%20reduction%20based%20on%20potential%20weights%20linear%20analysis%20to%20accelerate%20back%20propagation%20network.pdf Asadi, Roya and Mustapha, Norwati and Sulaiman, Md. Nasir (2009) Training process reduction based on potential weights linear analysis to accelerate back propagation network. International Journal of Computer Science and Information Security, 3 (1). pp. 229-239. ISSN 1947-5500 English
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
English
description Learning is the important property of Back Propagation Network (BPN) and finding the suitable weights and thresholds during training in order to improve training time as well as achieve high accuracy. Currently, data pre-processing such as dimension reduction input values and pre-training are the contributing factors in developing efficient techniques for reducing training time with high accuracy and initialization of the weights is the important issue which is random and creates paradox, and leads to low accuracy with high training time. One good data preprocessing technique for accelerating BPN classification is dimension reduction technique but it has problem of missing data. In this paper, we study current pre-training techniques and new preprocessing technique called Potential Weight Linear Analysis (PWLA) which combines normalization, dimension reduction input values and pre-training. In PWLA, the first data preprocessing is performed for generating normalized input values and then applying them by pre-training technique in order to obtain the potential weights. After these phases, dimension of input values matrix will be reduced by using real potential weights. For experiment results XOR problem and three datasets, which are SPECT Heart, SPECTF Heart and Liver disorders (BUPA) will be evaluated. Our results, however, will show that the new technique of PWLA will change BPN to new Supervised Multi Layer Feed Forward Neural Network (SMFFNN) model with high accuracy in one epoch without training cycle. Also PWLA will be able to have power of non linear supervised and unsupervised dimension reduction property for applying by other supervised multi layer feed forward neural network model in future work.
format Article
author Asadi, Roya
Mustapha, Norwati
Sulaiman, Md. Nasir
spellingShingle Asadi, Roya
Mustapha, Norwati
Sulaiman, Md. Nasir
Training process reduction based on potential weights linear analysis to accelerate back propagation network.
author_facet Asadi, Roya
Mustapha, Norwati
Sulaiman, Md. Nasir
author_sort Asadi, Roya
title Training process reduction based on potential weights linear analysis to accelerate back propagation network.
title_short Training process reduction based on potential weights linear analysis to accelerate back propagation network.
title_full Training process reduction based on potential weights linear analysis to accelerate back propagation network.
title_fullStr Training process reduction based on potential weights linear analysis to accelerate back propagation network.
title_full_unstemmed Training process reduction based on potential weights linear analysis to accelerate back propagation network.
title_sort training process reduction based on potential weights linear analysis to accelerate back propagation network.
publisher IJCSIS Press
publishDate 2009
url http://psasir.upm.edu.my/id/eprint/17465/1/Training%20process%20reduction%20based%20on%20potential%20weights%20linear%20analysis%20to%20accelerate%20back%20propagation%20network.pdf
http://psasir.upm.edu.my/id/eprint/17465/
_version_ 1643826525042114560
score 13.211869

Similar Items