The effects of using problem knowledge in a neural network for image processing tasks : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Palmerston North, New Zealand

Simple item page
dc.contributor.authorGunetileke, Kapila Sanjeeva
dc.date.accessioned2011-01-26T20:36:59Z
dc.date.availableNO_RESTRICTIONen_US
dc.date.available2011-01-26T20:36:59Z
dc.date.issued2001
dc.descriptionDigital and hard copy imperfect: P.1 missingen_US
dc.description.abstractThis thesis is concerned with aspects of computational intelligence. Computational intelligence is a new paradigm of artificial intelligence based on biological intelligence. Computational Intelligence explores the potential for biologically inspired intelligent adaptive machines and behavior. A relatively new and important sub discipline within the field of computational intelligence, is that of neural networks. Neural networks are networks of artificial neurons with a high degree of interconnectivity. The networks capture and accumulate knowledge as the pattern of weights in the interconnections between neurons. Neural networks are iteratively trained to perform tasks by "learning" from examples. These networks are often slow to train. One of the reasons for this is that the starting weights of the network are conventionally not related to the problem being solved. In this thesis a methodology is explored that maps problem knowledge to the starting weights of a fuzzy neural network window filter (FuNNWF). The FuNNWF architecture was developed from the combination of fuzzy logic and artificial neural networks for image processing tasks. The effects of the use of problem knowledge on FuNNWF training are investigated. The problem knowledge mapping procedure is extended from boolean rule mapping to conditional rule mapping, which allows better representation of the problems. Four real world image processing problems are investigated using the new weight initialization methodology. The experiments reported in this thesis demonstrate that the use of problem knowledge improves the robustness and convergence of the neural network. It is also shown that the use of the methodology is most effective on network training when the training data is noisy, unreliable and ambiguous.en_US
dc.identifier.urihttp://hdl.handle.net/10179/2106
dc.language.isoenen_US
dc.publisherMassey Universityen_US
dc.rightsThe Authoren_US
dc.subjectSoft computingen_US
dc.subjectComputational intelligenceen_US
dc.subjectNeural networks (Computer Science)en_US
dc.subjectImage processingen_US
dc.subjectComputer scienceen_US
dc.subject.otherFields of Research::280000 Information, Computing and Communication Sciences::280200 Artificial Intelligence and Signal and Image Processing::280203 Image processingen_US
dc.titleThe effects of using problem knowledge in a neural network for image processing tasks : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Palmerston North, New Zealanden_US
dc.typeThesisen_US
massey.contributor.authorGunetileke, Kapila Sanjeeva
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorMassey Universityen_US
thesis.degree.levelDoctoralen_US
thesis.degree.nameDoctor of Philosophy (Ph.D.)en_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
02_whole.pdf
Size:
7.4 MB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
01_front.pdf
Size:
764.75 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
896 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Theses and Dissertations