Improved spikeprop algorithm for neural network learning

Spiking Neural Network (SNN) utilizes individual spikes in time domain to communicate and to perform computation in a manner like what the real neurons actually do. SNN had remained unexplored for many years because it was considered too complex and too difficult to analyze. Since Sander Bothe intro...

Full description

Saved in:

Bibliographic Details
Main Author:	Ahmed, Falah Y. H.
Format:	Thesis
Language:	English
Published:	2013
Subjects:	QA Mathematics
Online Access:	http://eprints.utm.my/id/eprint/33796/5/FalahYHAhmedPFSKSM2013.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.33796
record_format	uketd_dc
spelling	my-utm-ep.337962017-07-18T06:14:34Z Improved spikeprop algorithm for neural network learning 2013-05 Ahmed, Falah Y. H. QA Mathematics Spiking Neural Network (SNN) utilizes individual spikes in time domain to communicate and to perform computation in a manner like what the real neurons actually do. SNN had remained unexplored for many years because it was considered too complex and too difficult to analyze. Since Sander Bothe introduced SpikeProp as a supervised learning model for SNN in 2002, many problems which were not clearly known regarding the characteristics of SNN have now been understood. Despite the success of Bohte in his pioneering work on SpikeProp, his algorithm is dictated by fixed time convergence in the iterative process to get optimum initial weights and the lengthy procedure in implementing the sequence of complete learning for classification purposes. Therefore, this thesis proposes an improvement to Bohte’s algorithm by introducing acceleration factors of Particle Swarm Optimization (PSO) denoted as Model 1; SpikeProp using ? Angle driven Learning rate dependency as Model 2; SpikeProp using Radius Initial Weight as Model 3a, and SpikeProp using Differential Evolution (DE) Weights Initialization as Model 3b.The hybridization of Model 1 and Model 2 gives Model 4, and finally Model 5 is obtained from the hybridization of Model 1, Model 3a and Model 3b. With these new methods, it was observed that the errors can be reduced accordingly. Training and classification properties of the new proposed methods were investigated using datasets from Machine Learning Benchmark Repository. Performance results of the proposed Models (for which graphs of time errors with iterative timings, table of number of iterations required to reduce time error measurement to saturation level and bar charts of accuracy at saturation time error for all the datasets have been plotted and drawn up) were compared with one another and with the performance results of Standard SpikeProp and Backpropagation (BP). Results indicated that the performances of Model 4, Model5 and Model 1 are better than Model 2, Model 3a and Model 3b. The findings also reveal that all the proposed models perform better than Standard SpikeProp and BP for all datasets used. 2013-05 Thesis http://eprints.utm.my/id/eprint/33796/ http://eprints.utm.my/id/eprint/33796/5/FalahYHAhmedPFSKSM2013.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:70130?site_name=Restricted Repository phd doctoral Universiti Teknologi Malaysia, Faculty of Computing Faculty of Computing
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA Mathematics
spellingShingle	QA Mathematics Ahmed, Falah Y. H. Improved spikeprop algorithm for neural network learning
description	Spiking Neural Network (SNN) utilizes individual spikes in time domain to communicate and to perform computation in a manner like what the real neurons actually do. SNN had remained unexplored for many years because it was considered too complex and too difficult to analyze. Since Sander Bothe introduced SpikeProp as a supervised learning model for SNN in 2002, many problems which were not clearly known regarding the characteristics of SNN have now been understood. Despite the success of Bohte in his pioneering work on SpikeProp, his algorithm is dictated by fixed time convergence in the iterative process to get optimum initial weights and the lengthy procedure in implementing the sequence of complete learning for classification purposes. Therefore, this thesis proposes an improvement to Bohte’s algorithm by introducing acceleration factors of Particle Swarm Optimization (PSO) denoted as Model 1; SpikeProp using ? Angle driven Learning rate dependency as Model 2; SpikeProp using Radius Initial Weight as Model 3a, and SpikeProp using Differential Evolution (DE) Weights Initialization as Model 3b.The hybridization of Model 1 and Model 2 gives Model 4, and finally Model 5 is obtained from the hybridization of Model 1, Model 3a and Model 3b. With these new methods, it was observed that the errors can be reduced accordingly. Training and classification properties of the new proposed methods were investigated using datasets from Machine Learning Benchmark Repository. Performance results of the proposed Models (for which graphs of time errors with iterative timings, table of number of iterations required to reduce time error measurement to saturation level and bar charts of accuracy at saturation time error for all the datasets have been plotted and drawn up) were compared with one another and with the performance results of Standard SpikeProp and Backpropagation (BP). Results indicated that the performances of Model 4, Model5 and Model 1 are better than Model 2, Model 3a and Model 3b. The findings also reveal that all the proposed models perform better than Standard SpikeProp and BP for all datasets used.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Ahmed, Falah Y. H.
author_facet	Ahmed, Falah Y. H.
author_sort	Ahmed, Falah Y. H.
title	Improved spikeprop algorithm for neural network learning
title_short	Improved spikeprop algorithm for neural network learning
title_full	Improved spikeprop algorithm for neural network learning
title_fullStr	Improved spikeprop algorithm for neural network learning
title_full_unstemmed	Improved spikeprop algorithm for neural network learning
title_sort	improved spikeprop algorithm for neural network learning
granting_institution	Universiti Teknologi Malaysia, Faculty of Computing
granting_department	Faculty of Computing
publishDate	2013
url	http://eprints.utm.my/id/eprint/33796/5/FalahYHAhmedPFSKSM2013.pdf
_version_	1747816187260043264

Improved spikeprop algorithm for neural network learning

Similar Items