Parallel implementation on improved error signal of backpropagation algorithm
The research work presented in this thesis is a continuation of Shamsuddin's work regarding proposed error signal for the backpropagation (BP) algorithm. The main focus is to parallelise Shamsuddin's work in order to improve the speedup of the BP algorithm. The experiments are implemen...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | English |
Published: |
2001
|
Subjects: | |
Online Access: | http://psasir.upm.edu.my/id/eprint/8669/1/FSKTM_2001_10%20IR.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-upm-ir.8669 |
---|---|
record_format |
uketd_dc |
spelling |
my-upm-ir.86692023-12-26T01:23:29Z Parallel implementation on improved error signal of backpropagation algorithm 2001-05 Mohd Aris, Teh Noranis The research work presented in this thesis is a continuation of Shamsuddin's work regarding proposed error signal for the backpropagation (BP) algorithm. The main focus is to parallelise Shamsuddin's work in order to improve the speedup of the BP algorithm. The experiments are implemented using the Sequent Symmetry SE30 parallel machine. The BP algorithm uses the data partitioning method with columnwise block striped and the batch mode weight updating strategy. Twenty-six patterns consisting of uppercase letters from 'A' to 'Z' are tested in the experiments. Two main factors taken into consideration in this, experiments are the execution time and speedup and the recognition rates. Shamsuddin's proposed BP parallel version, is compared with the sequential version. Experimental results shows that the execution time of the parallel version is much less than the execution time of the sequential version. The parallel version produces a good speedup as the number of processors, are increased due to the value that is near the ideal value. Experiments for testing the recognition rates involves the twenty-six trained sample data with perfect pattern and untrained sample data with 10% corrupted pattern. The recognition rates results show 100% accuracy for the trained and untrained data using the standard BP and Shamsuddin's proposed BP running sequentially. Back propagation (Artificial intelligence) Parallel processing (Electronic computers) Error messages (Computer science) 2001-05 Thesis http://psasir.upm.edu.my/id/eprint/8669/ http://psasir.upm.edu.my/id/eprint/8669/1/FSKTM_2001_10%20IR.pdf text en public masters Universiti Putra Malaysia Back propagation (Artificial intelligence) Parallel processing (Electronic computers) Error messages (Computer science) Faculty of Computer Science and Information Technology Mohd Saman, Md. Yazid |
institution |
Universiti Putra Malaysia |
collection |
PSAS Institutional Repository |
language |
English |
advisor |
Mohd Saman, Md. Yazid |
topic |
Back propagation (Artificial intelligence) Parallel processing (Electronic computers) Error messages (Computer science) |
spellingShingle |
Back propagation (Artificial intelligence) Parallel processing (Electronic computers) Error messages (Computer science) Mohd Aris, Teh Noranis Parallel implementation on improved error signal of backpropagation algorithm |
description |
The research work presented in this thesis is a continuation of
Shamsuddin's work regarding proposed error signal for the
backpropagation (BP) algorithm. The main focus is to parallelise
Shamsuddin's work in order to improve the speedup of the BP algorithm.
The experiments are implemented using the Sequent Symmetry SE30
parallel machine. The BP algorithm uses the data partitioning method with
columnwise block striped and the batch mode weight updating strategy.
Twenty-six patterns consisting of uppercase letters from 'A' to 'Z' are tested
in the experiments. Two main factors taken into consideration in this,
experiments are the execution time and speedup and the recognition rates. Shamsuddin's proposed BP parallel version, is compared with the
sequential version. Experimental results shows that the execution time of
the parallel version is much less than the execution time of the sequential
version. The parallel version produces a good speedup as the number of
processors, are increased due to the value that is near the ideal value.
Experiments for testing the recognition rates involves the twenty-six
trained sample data with perfect pattern and untrained sample data with
10% corrupted pattern. The recognition rates results show 100% accuracy
for the trained and untrained data using the standard BP and Shamsuddin's
proposed BP running sequentially. |
format |
Thesis |
qualification_level |
Master's degree |
author |
Mohd Aris, Teh Noranis |
author_facet |
Mohd Aris, Teh Noranis |
author_sort |
Mohd Aris, Teh Noranis |
title |
Parallel implementation on improved error signal of backpropagation algorithm |
title_short |
Parallel implementation on improved error signal of backpropagation algorithm |
title_full |
Parallel implementation on improved error signal of backpropagation algorithm |
title_fullStr |
Parallel implementation on improved error signal of backpropagation algorithm |
title_full_unstemmed |
Parallel implementation on improved error signal of backpropagation algorithm |
title_sort |
parallel implementation on improved error signal of backpropagation algorithm |
granting_institution |
Universiti Putra Malaysia |
granting_department |
Faculty of Computer Science and Information Technology |
publishDate |
2001 |
url |
http://psasir.upm.edu.my/id/eprint/8669/1/FSKTM_2001_10%20IR.pdf |
_version_ |
1794018769874452480 |