Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11889/4220
Title: Mussels wandering optimization algorithm based training of artificial neural networks for pattern classification
Authors: Abu Snaina, Ahmed
Abdullah, Rosni
Keywords: Artificial intelligence
Neural networks (Computer science)
Issue Date: 2013
Abstract: Training an artificial neural network (ANN) is an optimization task since it is desired to find optimal neurons‘ weight of a neural network in an iterative training process. Traditional training algorithms have some drawbacks such as local minima and its slowness. Therefore, evolutionary algorithms are utilized to train neural networks to overcome these issues. This research tackles the ANN training by adapting Mussels Wandering Optimization (MWO) algorithm. The proposed method tested and verified by training an ANN with well-known benchmarking problems. Two criteria used to evaluate the proposed method were overall training time and classification accuracy. The obtained results indicate that MWO algorithm is on par or better in terms of classification accuracy and convergence training time.
URI: http://hdl.handle.net/20.500.11889/4220
Appears in Collections:Fulltext Publications

Files in This Item:
File Description SizeFormat 
PID105.pdf727.55 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.