Abusnaina, Ahmed A. and Abdullah, Rosni (2013) Mussels wandering optimization algorithmn based training of artificial neural networks for pattern classification. In: 4th International Conference on Computing and Informatics (ICOCI 2013), 28 -30 August 2013, Kuching, Sarawak, Malaysia.

PDF Restricted to Registered users only Download (749kB) | Request a copy

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.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	ISBN: 9789832078791 Organized by: Universiti Utara Malaysia
Uncontrolled Keywords:	Artificial neural network, Mussels Wandering Optimization, supervised training, Optimization, Evolutionary algorithms
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Divisions:	College of Arts and Sciences
Depositing User:	Mrs. Norazmilah Yaakub
Date Deposited:	24 Aug 2014 02:36
Last Modified:	24 Aug 2014 02:36
URI:	https://repo.uum.edu.my/id/eprint/11972

Actions (login required)

View Item