OpenAIR OpenAIR
 
 

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

Please use this identifier to cite or link to this item: http://hdl.handle.net/10059/241
This item has been viewed 48 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Thesis - Combined content for printings.pdf19.05 MBAdobe PDFView/Open
Title: The functionality of spatial and time domain artificial neural models
Authors: Capanni, Niccolo Francesco
Supervisors: MacLeod, Christopher
Maxwell, Grant M.
Keywords: Artificial neural networks
Artificial neurons
Taylor Series neuron
Power Series theory
Evolutionary networks
Genetic algorithms
Artificial intelligence
Artificial biochemical networks
Parallel distributed processing
Issue Date: Aug-2006
Publisher: The Robert Gordon University
Citation: CAPANNI, M.F., MACLEOD, C., MAXWELL, G., 2003. An approach to evolvable neural functionality, ICANN-ICONIP, Joint International Conference on Neural Information Processing, Istanbul, Turkey, Proceedings supplementary volume for short papers, pp. 220-223
CAPANNI, N., MACLEOD, C., MAXWELL, G. and CLAYTON, W., 2005. Artificial biochemical networks. Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on Volume 2, 28-30 Nov. 2005 Page(s):98 - 102
Abstract: This thesis investigates the functionality of the units used in connectionist Artificial Intelligence systems. Artificial Neural Networks form the foundation of the research and their units, Artificial Neurons, are first compared with alternative models. This initial work is mainly in the spatial-domain and introduces a new neural model, termed a Taylor Series neuron. This is designed to be flexible enough to assume most mathematical functions. The unit is based on Power Series theory and a specifically implemented Taylor Series neuron is demonstrated. These neurons are of particular usefulness in evolutionary networks as they allow the complexity to increase without adding units. Training is achieved via various traditiona and derived methods based on the Delta Rule, Backpropagation, Genetic Algorithms and associated evolutionary techniques. This new neural unit has been presented as a controllable and more highly functional alternative to previous models. The work on the Taylor Series neuron moved into time-domain behaviour and through the investigation of neural oscillators led to an examination of single-celled intelligence from which the later work developed. Connectionist approaches to Artificial Intelligence are almost always based on Artificial Neural Networks. However, another route towards Parallel Distributed Processing was introduced. This was inspired by the intelligence displayed by single-celled creatures called Protoctists (Protists). A new system based on networks of interacting proteins was introduced. These networks were tested in pattern-recognition and control tasks in the time-domain and proved more flexible than most neuron models. They were trained using a Genetic Algorithm and a derived Backpropagation Algorithm. Termed "Artificial BioChemical Networks" (ABN) they have been presented as an alternative approach to connectionist systems.
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, Schoolhill, Aberdeen, AB10 1FR, Scotland, UK: a Scottish charity, registration No. SCO13781