Functional link neural network with modified bee-firefly learning algorithm for classification task
Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs). The ANNs are capable of generating a complex mapping between the input and the output space to form arbitrarily complex nonlinear decision boundaries. One of the best-known types of ANNs is the Multil...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | en en en |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/10076/2/24p%20YANA%20MAZWIN%20MOHMAD%20HASSIM.pdf http://eprints.uthm.edu.my/10076/1/YANA%20MAZWIN%20MOHMAD%20HASSIM%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/10076/3/YANA%20MAZWIN%20MOHMAD%20HASSIM%20WATERMARK.pdf http://eprints.uthm.edu.my/10076/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833419136896598016 |
|---|---|
| author | Mohmad Hassim, Yana Mazwin |
| author_facet | Mohmad Hassim, Yana Mazwin |
| author_sort | Mohmad Hassim, Yana Mazwin |
| building | UTHM Library |
| collection | Institutional Repository |
| content_provider | Universiti Tun Hussein Onn Malaysia |
| content_source | UTHM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs). The ANNs are capable of generating a complex mapping between the input and the output space to form arbitrarily complex nonlinear decision boundaries. One of the best-known types of ANNs is the Multilayer Perceptron (MLP). MLP usually requires a large amount of available measures in order to achieve good classification accuracy. To overcome this, a Functional Link Neural Networks (FLNN) which has a single layer of trainable connection weights is used. The single layer property of FLNN also make the learning algorithm used less complicated compared to MLP network. The standard learning method for tuning weights in FLNN is Backpropagation (BP) learning algorithm. However, the algorithm is prone to get trapped in local minima which affect the performance of FLNN network. This work proposed the implementation of modified Artificial Bee Colony with Firefly algorithm for training the FLNN network to overcome the drawback of BP-learning algorithm. The aim is to introduce an improved learning algorithm that can provide a better solution for training the FLNN network for the task of classification |
| format | Thesis |
| id | my.uthm.eprints-10076 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | en en en |
| publishDate | 2016 |
| record_format | eprints |
| spelling | my.uthm.eprints-100762023-10-11T03:24:00Z http://eprints.uthm.edu.my/10076/ Functional link neural network with modified bee-firefly learning algorithm for classification task Mohmad Hassim, Yana Mazwin QA Mathematics QA76 Computer software Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs). The ANNs are capable of generating a complex mapping between the input and the output space to form arbitrarily complex nonlinear decision boundaries. One of the best-known types of ANNs is the Multilayer Perceptron (MLP). MLP usually requires a large amount of available measures in order to achieve good classification accuracy. To overcome this, a Functional Link Neural Networks (FLNN) which has a single layer of trainable connection weights is used. The single layer property of FLNN also make the learning algorithm used less complicated compared to MLP network. The standard learning method for tuning weights in FLNN is Backpropagation (BP) learning algorithm. However, the algorithm is prone to get trapped in local minima which affect the performance of FLNN network. This work proposed the implementation of modified Artificial Bee Colony with Firefly algorithm for training the FLNN network to overcome the drawback of BP-learning algorithm. The aim is to introduce an improved learning algorithm that can provide a better solution for training the FLNN network for the task of classification 2016-08 Thesis NonPeerReviewed text en http://eprints.uthm.edu.my/10076/2/24p%20YANA%20MAZWIN%20MOHMAD%20HASSIM.pdf text en http://eprints.uthm.edu.my/10076/1/YANA%20MAZWIN%20MOHMAD%20HASSIM%20COPYRIGHT%20DECLARATION.pdf text en http://eprints.uthm.edu.my/10076/3/YANA%20MAZWIN%20MOHMAD%20HASSIM%20WATERMARK.pdf Mohmad Hassim, Yana Mazwin (2016) Functional link neural network with modified bee-firefly learning algorithm for classification task. Doctoral thesis, Universiti Tun Hussein Onn Malaysia. |
| spellingShingle | QA Mathematics QA76 Computer software Mohmad Hassim, Yana Mazwin Functional link neural network with modified bee-firefly learning algorithm for classification task |
| title | Functional link neural network with modified bee-firefly learning algorithm for classification task |
| title_full | Functional link neural network with modified bee-firefly learning algorithm for classification task |
| title_fullStr | Functional link neural network with modified bee-firefly learning algorithm for classification task |
| title_full_unstemmed | Functional link neural network with modified bee-firefly learning algorithm for classification task |
| title_short | Functional link neural network with modified bee-firefly learning algorithm for classification task |
| title_sort | functional link neural network with modified bee-firefly learning algorithm for classification task |
| topic | QA Mathematics QA76 Computer software |
| url | http://eprints.uthm.edu.my/10076/2/24p%20YANA%20MAZWIN%20MOHMAD%20HASSIM.pdf http://eprints.uthm.edu.my/10076/1/YANA%20MAZWIN%20MOHMAD%20HASSIM%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/10076/3/YANA%20MAZWIN%20MOHMAD%20HASSIM%20WATERMARK.pdf http://eprints.uthm.edu.my/10076/ |
| url_provider | http://eprints.uthm.edu.my/ |