Show simple item record

dc.contributor.advisorMacleod, Christopher
dc.contributor.advisorMaxwell, Grant M.
dc.contributor.authorCapanni, Niccolo Francesco
dc.date.accessioned2008-11-04T14:06:35Z
dc.date.available2008-11-04T14:06:35Z
dc.date.issued2006-08
dc.identifier.urihttp://hdl.handle.net/10059/241
dc.description.abstractThis 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.en
dc.format.extent19511608 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherThe Robert Gordon Universityen
dc.relationCAPANNI, 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. 220-223en
dc.relationCAPANNI, 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 - 102en
dc.rightsCopyright : Niccolo Francesco Capanni. Copyright for the first paper in Appendix A : Springer-Verlag. Copyright for the second paper in Appendix A : IEEE. Copyright ©2005 IEEE. Reprinted from Capanni, N.; MacLeod, C.; Maxwell, G.; Clayton, W.; 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 Digital Object Identifier 10.1109/CIMCA.2005.1631452 This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of The Robert Gordon University's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org.en
dc.subjectArtificial neural networksen
dc.subjectArtificial neuronsen
dc.subjectTaylor Series neuronen
dc.subjectPower Series theoryen
dc.subjectEvolutionary networksen
dc.subjectGenetic algorithmsen
dc.subjectArtificial intelligenceen
dc.subjectArtificial biochemical networksen
dc.subjectParallel distributed processingen
dc.titleThe functionality of spatial and time domain artificial neural modelsen
dc.typeTheses and dissertationsen
dc.publisher.departmentSchool of Engineeringen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhDen


Files in this item

This item appears in the following Collection(s)

Show simple item record