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...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohmad Hassim, Yana Mazwin
Format:	Thesis
Language:	English English English
Published:	2016
Subjects:	QA Mathematics QA76 Computer software
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
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.10076
record_format	uketd_dc
spelling	my-uthm-ep.100762023-10-11T03:24:00Z Functional link neural network with modified bee-firefly learning algorithm for classification task 2016-08 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 http://eprints.uthm.edu.my/10076/ http://eprints.uthm.edu.my/10076/2/24p%20YANA%20MAZWIN%20MOHMAD%20HASSIM.pdf text en public http://eprints.uthm.edu.my/10076/1/YANA%20MAZWIN%20MOHMAD%20HASSIM%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/10076/3/YANA%20MAZWIN%20MOHMAD%20HASSIM%20WATERMARK.pdf text en validuser phd doctoral Universiti Tun Hussein Onn Malaysia Fakulti Sains Komputer dan Teknologi Maklumat
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	QA Mathematics QA76 Computer software
spellingShingle	QA Mathematics QA76 Computer software Mohmad Hassim, Yana Mazwin Functional link neural network with modified bee-firefly learning algorithm for classification task
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
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Mohmad Hassim, Yana Mazwin
author_facet	Mohmad Hassim, Yana Mazwin
author_sort	Mohmad Hassim, Yana Mazwin
title	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_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_sort	functional link neural network with modified bee-firefly learning algorithm for classification task
granting_institution	Universiti Tun Hussein Onn Malaysia
granting_department	Fakulti Sains Komputer dan Teknologi Maklumat
publishDate	2016
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
_version_	1783728984257724416

Functional link neural network with modified bee-firefly learning algorithm for classification task

Similar Items