Mussels wandering optimization algorithmn based training of artificial neural networks for pattern classification
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 a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://repo.uum.edu.my/11972/1/PID105.pdf http://repo.uum.edu.my/11972/ http://www.icoci.cms.net.my/proceedings/2013/TOC.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Utara Malaysia |
| Language: | English |
| Summary: | 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. |
|---|