Award Date

12-1-2021

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Committee Member

Evangelos Yfantis

Second Committee Member

Andreas Stefik

Third Committee Member

John Minor

Fourth Committee Member

Sarah Harris

Number of Pages

98

Abstract

In the field of Computer Science, neural networks and genetic algorithms have become very popular tools in solving complex problems. Because of this growing popularity, there has been several attempts to combine the two concepts. Some of these attempts focused on using genetic algorithms to determine the best architecture, starting weights, or feature selection, to name of few of the applications. While a lot of the research that is available focuses on solving more than one element of the neural network design or is looking to use genetic algorithms to replace a part of the traditional neural network, such as back propagation, in this paper we focus on solving one key element of the network. We will show that it is possible to use a genetic algorithm to determine the best learning rate to be used when training a network, as opposed to the simple manual trial-and-error method that is used by most in the field today.

Controlled Subject

Neural networks (Computer science); Genetic algorithms; Learning

Disciplines

Computer Sciences

File Format

pdf

File Size

1424 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Download


Share

COinS