You are here

FAU Collections » FAU Research Repository » FAU Theses and Dissertations

new GMDH type algorithm for the development of neural networks for pattern recognition

Download pdf | Full Screen View

Date Issued:
2002
Summary:
Researchers from a wide range of fields have discovered the benefits of applying neural networks to pattern recognition problems. Although applications for neural networks have increased, development of tools to design these networks has been slower. There are few comprehensive network development methods. Those that do exist are slow, inefficient, and application specific, require predetermination of the final network structure, and/or result in large, complicated networks. Finding optimal neural networks that balance low network complexity with accuracy is a complicated process that traditional network development procedures are incapable of achieving. Although not originally designed for neural networks, the Group Method of Data Handling (GMDH) has characteristics that are ideal for neural network design. GMDH minimizes the number of required neurons by choosing and keeping only the best neurons and filtering out unneeded inputs. In addition, GMDH develops the neurons and organizes the network simultaneously, saving time and processing power. However, some of the qualities of the network must still be predetermined. This dissertation introduces a new algorithm that applies some of the best characteristics of GMDH to neural network design. The new algorithm is faster, more flexible, and more accurate than traditional network development methods. It is also more dynamic than current GMDH based methods, capable of creating a network that is optimal for an application and training data. Additionally, the new algorithm virtually guarantees that the number of neurons progressively decreases in each succeeding layer. To show its flexibility, speed, and ability to design optimal networks, the algorithm was used to successfully design networks for a wide variety of real applications. The networks developed using the new algorithm were compared to other development methods and network architectures. The new algorithm's networks were more accurate and yet less complicated than the other networks. Additionally, the algorithm designs neurons that are flexible enough to meet the needs of the specific applications, yet similar enough to be implemented using a standardized hardware cell. When combined with the simplified network layout that naturally occurs with the algorithm, this results in networks that can be implemented using Field Programmable Gate Array (FPGA) type devices.
Title: A new GMDH type algorithm for the development of neural networks for pattern recognition.
64 views
10 downloads
Name(s): Gilbar, Thomas C.
Florida Atlantic University, Degree grantor
Pandya, Abhijit S., Thesis advisor
College of Engineering and Computer Science
Department of Computer and Electrical Engineering and Computer Science
Type of Resource: text
Genre: Electronic Thesis Or Dissertation
Issuance: monographic
Date Issued: 2002
Publisher: Florida Atlantic University
Place of Publication: Boca Raton, Fla.
Physical Form: application/pdf
Extent: 187 p.
Language(s): English
Summary: Researchers from a wide range of fields have discovered the benefits of applying neural networks to pattern recognition problems. Although applications for neural networks have increased, development of tools to design these networks has been slower. There are few comprehensive network development methods. Those that do exist are slow, inefficient, and application specific, require predetermination of the final network structure, and/or result in large, complicated networks. Finding optimal neural networks that balance low network complexity with accuracy is a complicated process that traditional network development procedures are incapable of achieving. Although not originally designed for neural networks, the Group Method of Data Handling (GMDH) has characteristics that are ideal for neural network design. GMDH minimizes the number of required neurons by choosing and keeping only the best neurons and filtering out unneeded inputs. In addition, GMDH develops the neurons and organizes the network simultaneously, saving time and processing power. However, some of the qualities of the network must still be predetermined. This dissertation introduces a new algorithm that applies some of the best characteristics of GMDH to neural network design. The new algorithm is faster, more flexible, and more accurate than traditional network development methods. It is also more dynamic than current GMDH based methods, capable of creating a network that is optimal for an application and training data. Additionally, the new algorithm virtually guarantees that the number of neurons progressively decreases in each succeeding layer. To show its flexibility, speed, and ability to design optimal networks, the algorithm was used to successfully design networks for a wide variety of real applications. The networks developed using the new algorithm were compared to other development methods and network architectures. The new algorithm's networks were more accurate and yet less complicated than the other networks. Additionally, the algorithm designs neurons that are flexible enough to meet the needs of the specific applications, yet similar enough to be implemented using a standardized hardware cell. When combined with the simplified network layout that naturally occurs with the algorithm, this results in networks that can be implemented using Field Programmable Gate Array (FPGA) type devices.
Identifier: 9780493706221 (isbn), 11994 (digitool), FADT11994 (IID), fau:8911 (fedora)
Collection: FAU Electronic Theses and Dissertations Collection
Note(s): College of Engineering and Computer Science
Thesis (Ph.D.)--Florida Atlantic University, 2002.
Subject(s): GMDH algorithms
Neural networks (Computer science)
Pattern recognition systems
Held by: Florida Atlantic University Libraries
Persistent Link to This Record: http://purl.flvc.org/fcla/dt/11994
Sublocation: Digital Library
Use and Reproduction: Copyright © is held by the author, with permission granted to Florida Atlantic University to digitize, archive and distribute this item for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires permission of the copyright holder.
Use and Reproduction: http://rightsstatements.org/vocab/InC/1.0/
Host Institution: FAU
Is Part of Series: Florida Atlantic University Digital Library Collections.