OpenAIR @ RGU >
Design and Technology >
Engineering >
Theses (Engineering) >

Please use this identifier to cite or link to this item:
This item has been viewed 33 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
AMuthurumanThesisTitle.pdf54.8 kBAdobe PDFView/Open
BMuthuramanThesisAcknowledgements.pdf54.36 kBAdobe PDFView/Open
CMuthuramanThesisAbstract.pdf46.33 kBAdobe PDFView/Open
DMuthuramanThesisContents.pdf80.12 kBAdobe PDFView/Open
EMuthuramanThesisChapter1.pdf147.1 kBAdobe PDFView/Open
FMuthuramanThesisChapter2.pdf236.83 kBAdobe PDFView/Open
GMuthuramanThesisChapter3.pdf285.27 kBAdobe PDFView/Open
HMuthuramanThesisChapter4.pdf238.6 kBAdobe PDFView/Open
IMuthuramanThesisChapter5.pdf261.17 kBAdobe PDFView/Open
JMuthuramanThesisChapter6.pdf764.09 kBAdobe PDFView/Open
KMuthuramanThesisChapter7.pdf406.08 kBAdobe PDFView/Open
LMuthuramanThesisChapter8.pdf316.45 kBAdobe PDFView/Open
MMuthuramanThesisChapter9.pdf132.77 kBAdobe PDFView/Open
NMuthuramanThesisChapter10.pdf127.83 kBAdobe PDFView/Open
OMuthuramanThesisReferences.pdf149.43 kBAdobe PDFView/Open
PMuthuramanThesisAppendixA.pdf66.1 kBAdobe PDFView/Open
QMuthuramanThesisAppendixB.pdf43.68 kBAdobe PDFView/Open
RMuthuramanThesisAppendixC.pdf268.46 kBAdobe PDFView/Open
SMuthuramanThesisAppendixD.pdf70.93 kBAdobe PDFView/Open
TMuthuramanThesisAppendixE.pdf157.42 kBAdobe PDFView/Open
Title: The evolution of modular artificial neural networks
Authors: Muthuraman, Sethuraman
Supervisors: Maxwell, Grant M.
MacLeod, Christopher
Keywords: Artificial neural networks
Evolutionary algorithms
Genetic algorithms
Issue Date: 2005
Publisher: The Robert Gordon University
Abstract: This thesis describes a novel approach to the evolution of Modular Artificial Neural Networks. Standard Evolutionary Algorithms, used in this application include: Genetic Algorithms, Evolutionary Strategies, Evolutionary Programming and Genetic Programming; however, these often fail in the evolution of complex systems, particularly when such systems involve multi-domain sensory information which interacts in complex ways with system outputs. The aim in this work is to produce an evolutionary method that allows the structure of the network to evolve from simple to complex as it interacts with a dynamic environment. This new algorithm is therefore based on Incremental Evolution. A simulated model of a legged robot was used as a test-bed for the approach. The algorithm starts with a simple robotic body plan. This then grows incrementally in complexity along with its controlling neural network and the environment it reacts with. The network grows by adding modules to its structure - so the technique may also be termed a Growth Algorithm. Experiments are presented showing the successful evolution of multi-legged gaits and a simple vision system. These are then integrated together to form a complete robotic system. The possibility of the evolution of complex systems is one advantage of the algorithm and it is argued that it represents a possible path towards more advanced artificial intelligence. Applications in Electronics, Computer Science, Mechanical Engineering and Aerospace are also discussed.
Appears in Collections:Theses (Engineering)

All items in OpenAIR are protected by copyright, with all rights reserved.


   Disclaimer | Freedom of Information | Privacy Statement |Copyright ©2012 Robert Gordon University, Garthdee House, Garthdee Road, Aberdeen, AB10 7QB, Scotland, UK: a Scottish charity, registration No. SC013781