Cover Image

PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM

An artificial neural network (ANN), or shortly "neural network" (NN), is a powerful mathematical or computational model that is inspired by the structure and/or functional characteristics of biological neural networks. Despite the fact that ANN has been developing rapidly for many years...

Full description

Saved in:
Bibliographic Details
Main Author: AHMED ABDALLA, OSMAN
Format: Thesis
Language:English
Published: 2011
Online Access:http://utpedia.utp.edu.my/2846/1/my_thesis_osman30-1-2001...last7.pdf
http://utpedia.utp.edu.my/2846/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-utp-utpedia.2846
record_format eprints
spelling my-utp-utpedia.28462017-01-25T09:42:43Z http://utpedia.utp.edu.my/2846/ PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM AHMED ABDALLA, OSMAN An artificial neural network (ANN), or shortly "neural network" (NN), is a powerful mathematical or computational model that is inspired by the structure and/or functional characteristics of biological neural networks. Despite the fact that ANN has been developing rapidly for many years, there are still some challenges concerning the development of an ANN model that performs effectively for the problem at hand. ANN can be categorized into three main types: single layer, recurrent network and multilayer feed-forward network. In multilayer feed-forward ANN, the actual performance is highly dependent on the selection of architecture and training parameters. However, a systematic method for optimizing these parameters is still an active research area. This work focuses on multilayer feed-forward ANNs due to their generalization capability, simplicity from the viewpoint of structure, and ease of mathematical analysis. Even though, several rules for the optimization of multilayer feed-forward ANN parameters are available in the literature, most networks are still calibrated via a trial-and-error procedure, which depends mainly on the type of problem, and past experience and intuition of the expert. To overcome these limitations, there have been attempts to use genetic algorithm (GA) to optimize some of these parameters. However most, if not all, of the existing approaches are focused partially on the part of architecture and training parameters. On the contrary, the GAANN approach presented here has covered most aspects of multilayer feed-forward ANN in a more comprehensive way. This research focuses on the use of binaryencoded genetic algorithm (GA) to implement efficient search strategies for the optimal architecture and training parameters of a multilayer feed-forward ANN. Particularly, GA is utilized to determine the optimal number of hidden layers, number of neurons in each hidden layer, type of training algorithm, type of activation function of hidden and output neurons, initial weight, learning rate, momentum term, and epoch size of a multilayer feed-forward ANN. In this thesis, the approach has been analyzed and algorithms that simulate the new approach have been mapped out. The approach has been tested in three actual operations, in addition to standard XOR problem; where the results have shown the applicability of the proposed approach in those applications. The proposed method is considered novel as it has proven that GA-based method can be comprehensively utilized to determine multilayer feedforward ANN architecture and training parameters. This method is more effective and gives a more precise performance than existing approaches, in addition to being less human dependent. It also has a better generalization capability and training stability. In summary, the main contributions of this research are: demonstrates the strength of genetic algorithm (GA), auto designing of multilayer feed-forward ANN, and demonstrates the hybridization capability of GA with multilayer feed-forward ANN. 2011 Thesis NonPeerReviewed application/pdf en http://utpedia.utp.edu.my/2846/1/my_thesis_osman30-1-2001...last7.pdf AHMED ABDALLA, OSMAN (2011) PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM. PhD thesis, UTP.
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Electronic and Digitized Intellectual Asset
url_provider http://utpedia.utp.edu.my/
language English
description An artificial neural network (ANN), or shortly "neural network" (NN), is a powerful mathematical or computational model that is inspired by the structure and/or functional characteristics of biological neural networks. Despite the fact that ANN has been developing rapidly for many years, there are still some challenges concerning the development of an ANN model that performs effectively for the problem at hand. ANN can be categorized into three main types: single layer, recurrent network and multilayer feed-forward network. In multilayer feed-forward ANN, the actual performance is highly dependent on the selection of architecture and training parameters. However, a systematic method for optimizing these parameters is still an active research area. This work focuses on multilayer feed-forward ANNs due to their generalization capability, simplicity from the viewpoint of structure, and ease of mathematical analysis. Even though, several rules for the optimization of multilayer feed-forward ANN parameters are available in the literature, most networks are still calibrated via a trial-and-error procedure, which depends mainly on the type of problem, and past experience and intuition of the expert. To overcome these limitations, there have been attempts to use genetic algorithm (GA) to optimize some of these parameters. However most, if not all, of the existing approaches are focused partially on the part of architecture and training parameters. On the contrary, the GAANN approach presented here has covered most aspects of multilayer feed-forward ANN in a more comprehensive way. This research focuses on the use of binaryencoded genetic algorithm (GA) to implement efficient search strategies for the optimal architecture and training parameters of a multilayer feed-forward ANN. Particularly, GA is utilized to determine the optimal number of hidden layers, number of neurons in each hidden layer, type of training algorithm, type of activation function of hidden and output neurons, initial weight, learning rate, momentum term, and epoch size of a multilayer feed-forward ANN. In this thesis, the approach has been analyzed and algorithms that simulate the new approach have been mapped out. The approach has been tested in three actual operations, in addition to standard XOR problem; where the results have shown the applicability of the proposed approach in those applications. The proposed method is considered novel as it has proven that GA-based method can be comprehensively utilized to determine multilayer feedforward ANN architecture and training parameters. This method is more effective and gives a more precise performance than existing approaches, in addition to being less human dependent. It also has a better generalization capability and training stability. In summary, the main contributions of this research are: demonstrates the strength of genetic algorithm (GA), auto designing of multilayer feed-forward ANN, and demonstrates the hybridization capability of GA with multilayer feed-forward ANN.
format Thesis
author AHMED ABDALLA, OSMAN
spellingShingle AHMED ABDALLA, OSMAN
PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM
author_facet AHMED ABDALLA, OSMAN
author_sort AHMED ABDALLA, OSMAN
title PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM
title_short PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM
title_full PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM
title_fullStr PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM
title_full_unstemmed PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM
title_sort proposed methodology for optimizing the training parameters of a multilayer feedforward artificial neural networks using a genetic algorithm
publishDate 2011
url http://utpedia.utp.edu.my/2846/1/my_thesis_osman30-1-2001...last7.pdf
http://utpedia.utp.edu.my/2846/
_version_ 1739830966648569856
score 13.211869

Similar Items