An approach to improve functional link neural network training using modified artificial bee colony for classification task
Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs). One of the best known types of ANNs is the Multilayer Perceptron (MLP). However, MLP usually requires a rather large amount of available measures in order to achieve good classification accuracy....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Kebangsaan Malaysia (UKM)
2012
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/8068/1/J4150_daa703866d7e7f2fead8565845ab5143.pdf |
| _version_ | 1796869693879877632 |
|---|---|
| author | Mohmad Hassim, Yana Mazwin Ghazali, Rozaida |
| author_facet | Mohmad Hassim, Yana Mazwin Ghazali, Rozaida |
| author_sort | Mohmad Hassim, Yana Mazwin |
| collection | UTHM |
| description | Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs). One
of the best known types of ANNs is the Multilayer Perceptron (MLP). However, MLP usually requires
a rather large amount of available measures in order to achieve good classification accuracy. To
overcome this, a Functional Link Neural Networks (FLNN), which has single layer of trainable
connection weight is used. The standard method for tuning the weight in FLNN is using a
Backpropagation (BP) learning algorithm. Still, BP-learning algorithm has difficulties such as
trapping in local optima and slow convergence especially for solving non-linearly separable
classification problems. In this paper, a modified Artificial Bee Colony (mABC) is used to recover the
BP drawbacks. With modifications on the employed bee’s exploitation phase, the implementation of
the mABC as a learning scheme for FLNN has given a better accuracy result for the classification
tasks. |
| first_indexed | 2024-03-05T21:58:34Z |
| format | Article |
| id | uthm.eprints-8068 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T21:58:34Z |
| publishDate | 2012 |
| publisher | Universiti Kebangsaan Malaysia (UKM) |
| record_format | dspace |
| spelling | uthm.eprints-80682022-12-06T02:55:41Z http://eprints.uthm.edu.my/8068/ An approach to improve functional link neural network training using modified artificial bee colony for classification task Mohmad Hassim, Yana Mazwin Ghazali, Rozaida T Technology (General) Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs). One of the best known types of ANNs is the Multilayer Perceptron (MLP). However, MLP usually requires a rather large amount of available measures in order to achieve good classification accuracy. To overcome this, a Functional Link Neural Networks (FLNN), which has single layer of trainable connection weight is used. The standard method for tuning the weight in FLNN is using a Backpropagation (BP) learning algorithm. Still, BP-learning algorithm has difficulties such as trapping in local optima and slow convergence especially for solving non-linearly separable classification problems. In this paper, a modified Artificial Bee Colony (mABC) is used to recover the BP drawbacks. With modifications on the employed bee’s exploitation phase, the implementation of the mABC as a learning scheme for FLNN has given a better accuracy result for the classification tasks. Universiti Kebangsaan Malaysia (UKM) 2012 Article PeerReviewed text en http://eprints.uthm.edu.my/8068/1/J4150_daa703866d7e7f2fead8565845ab5143.pdf Mohmad Hassim, Yana Mazwin and Ghazali, Rozaida (2012) An approach to improve functional link neural network training using modified artificial bee colony for classification task. ASIA-PACIFIC JOURNAL OF INFORMATION TECHNOLOGY AND MULTIMEDIA, 2 (2). pp. 63-71. ISSN 2289-2192 |
| spellingShingle | T Technology (General) Mohmad Hassim, Yana Mazwin Ghazali, Rozaida An approach to improve functional link neural network training using modified artificial bee colony for classification task |
| title | An approach to improve functional link neural network training using modified artificial bee colony for classification task |
| title_full | An approach to improve functional link neural network training using modified artificial bee colony for classification task |
| title_fullStr | An approach to improve functional link neural network training using modified artificial bee colony for classification task |
| title_full_unstemmed | An approach to improve functional link neural network training using modified artificial bee colony for classification task |
| title_short | An approach to improve functional link neural network training using modified artificial bee colony for classification task |
| title_sort | approach to improve functional link neural network training using modified artificial bee colony for classification task |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/8068/1/J4150_daa703866d7e7f2fead8565845ab5143.pdf |
| work_keys_str_mv | AT mohmadhassimyanamazwin anapproachtoimprovefunctionallinkneuralnetworktrainingusingmodifiedartificialbeecolonyforclassificationtask AT ghazalirozaida anapproachtoimprovefunctionallinkneuralnetworktrainingusingmodifiedartificialbeecolonyforclassificationtask AT mohmadhassimyanamazwin approachtoimprovefunctionallinkneuralnetworktrainingusingmodifiedartificialbeecolonyforclassificationtask AT ghazalirozaida approachtoimprovefunctionallinkneuralnetworktrainingusingmodifiedartificialbeecolonyforclassificationtask |