published_or_final_version / abstract / Chemistry / Master / Master of Philosophy

Functional parallel programming techniques for feed-forward artificial neural networks trained using backpropagation learning are analyzed. In particular, the Data Parallel Haskell extension to the Glasgow Haskell Compiler is considered as a tool for achieving data parallelism. We find much potential and elegance in this method, and determine that a sufficiently large workload is critical in achieving real gains. Several additional features are recommended to increase usability and improve results on small datasets. / text

Electronic book production is a developing field which is still in its infancy. As such, there is still relatively little material available in the form of design principles or guidelines for the production of such books. It is also extremely complex, in that electronic book designers can take advantage of a number of delivery techniques which are not available to authors of traditional paper-based books. Such techniques include: multimedia (the delivery of text, pictures, sound, and moving pictures); and hypermedia (the linking of reactive information items to form non-linear structures). This research investigates some of the key issues in the design of end-user interfaces to electronic books. Essentially, this centres on three basic problems: the use of metaphors in the design of interfaces to electronic books; models for the design of multimedia pages; and the provision of various knowledge corpus structures. Interface metaphors are investigated through the implementation and evaluation of the book metaphor. Applications were developed which either embedded or did not embed the book metaphor. Subjects used these applications while undertaking a number of information access tasks. Both qualitative and performance data werecollected and some significant results were obtained. Five page models were developed (referred to as: simple; tiled; overlay; oversize; and dynamic) which were used to design a number of page structures. These page structures were evaluated using qualitative measures of user reactions to the various page structures. Seven interface dimensions were measured and again significant results were obtained. To measure the effects of knowledge corpus structure on the design of electronic books three different book structures were created: linear; tree; and network. These were investigated in the light of some common information access tasks. The results indicated that some knowledge corpus structures were more appropriate for certain types of task.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

In recent years there has been a great interest in neural networks, since neural networks are capable of performing pattern recognition, classification, decision, search, and optimization. A key element of most neural network systems is the massive number of weighted interconnections (synapses) used to tie relatively simple processing elements (neurons) together in a useful architecture. The inherent parallelism and interconnection capability of optics make it a likely candidate for the implementation of the neural network interconnection process. While there are several optical technologies worth exploring, this dissertation examines the capabilities and limitations of using fixed planar holographic interconnects in a neural network system. While optics is well suited to the interconnection task, nonlinear processing operations are difficult to implement in optics and better suited to electronic implementations. Therefore, a hybrid neural network architecture of planar interconnection holograms and opto-electronic neurons is a sensible approach to implementing a neural network. This architecture is analyzed. The interconnection hologram must accurately encode synaptic weights, have a high diffraction efficiency, and maximize the number of interconnections. Various computer generated hologram techniques are tested for their ability to produce the interconnection hologram. A new technique using the Gerchberg-Saxton process followed by a random-search error minimization produces the highest interconnect accuracy and highest diffraction efficiency of the techniques tested. The analysis shows that a reasonable size planar hologram has a capacity to connect 5000 neuron outputs to 5000 neuron inputs and that the bipolar synaptic weights can have an accuracy of approximately 5 bits. To demonstrate the concept of an opto-electronic neural network and planar holographic interconnects, a Hopfield style associative memory is constructed and shown to perform almost as well as an ideal system.