Mohd Aris, Teh Noranis (2001) Parallel Implementation on Improved Error Signal of Backpropagation Algorithm. Masters thesis, Universiti Pertanian Malaysia.
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.
|Item Type:||Thesis (Masters)|
|Subject:||Back propagation (Artificial intelligence).|
|Subject:||Parallel processing (Electronic computers).|
|Subject:||Error messages (Computer science).|
|Chairman Supervisor:||Associate Professor Md. Yazid Mohd Saman, PhD|
|Call Number:||FSKTM 2001 10|
|Faculty or Institute:||Faculty of Computer Science and Information Technology|
|Deposited By:||Nurul Hayatie Hashim|
|Deposited On:||09 Dec 2010 02:23|
|Last Modified:||26 Jun 2012 06:45|
Repository Staff Only: item control page
Document Download Statistics
This item has been downloaded for since 09 Dec 2010 02:23.