Welcome To UTPedia

We would like to introduce you, the new knowledge repository product called UTPedia. The UTP Electronic and Digital Intellectual Asset. It stores digitized version of thesis, dissertation, final year project reports and past year examination questions.

Browse content of UTPedia using Year, Subject, Department and Author and Search for required document using Searching facilities included in UTPedia. UTPedia with full text are accessible for all registered users, whereas only the physical information and metadata can be retrieved by public users. UTPedia collaborating and connecting peoples with university’s intellectual works from anywhere.

Disclaimer - Universiti Teknologi PETRONAS shall not be liable for any loss or damage caused by the usage of any information obtained from this web site.Best viewed using Mozilla Firefox 3 or IE 7 with resolution 1024 x 768.

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

ABDALLA, OSMAN AHMED (2011) PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAINING PARAMETERS OF A MULTILAYER FEED-FORWARD ARTIFICIAL NEURAL NETWORKS USING A GENETIC ALGORITHM. PhD thesis, Universiti Teknologi Petronas.

[img] PDF
Download (4070Kb)

Abstract

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.

Item Type: Thesis (PhD)
Academic Subject : Academic Department - Information Communication Technology
Subject: UNSPECIFIED
Divisions: Sciences and Information Technology > Computer and Information Sciences
Depositing User: Users 2053 not found.
Date Deposited: 18 Jul 2013 15:58
Last Modified: 25 Jan 2017 09:42
URI: http://utpedia.utp.edu.my/id/eprint/6680

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...