No description available.

Many optical processing systems rely critically on the availability of high performance, electrically-addressed spatial light modulators. Ferroelectric liquid crystal over silicon is an attractive spatial light modulator technology because it combines two well matched technologies. Ferroelectric liquid crystal modulating materials exhibit fast switching times with low operating voltages, while very large scale silicon integrated circuits offer high-frequency, low power operation, and versatile functionality. This thesis describes the design and characterisation of the SBS256 - a general purpose 256 x 256 pixel ferroelectric liquid crystal over silicon spatial light modulator that incorporates a static-RAM latch and an exclusive-OR gate at each pixel. The static-RAM latch provides robust data storage under high read-beam intensities, while the exclusive-OR gate permits the liquid crystal layer to be fully and efficiently charge balanced. The SBS256 spatial light modulator operates in a binary mode. However, many applications, including helmet-mounted displays and optoelectronic implementations of artificial neural networks, require devices with some level of grey-scale capability. The 2 kHz frame rate of the device, permits temporal multiplexing to be used as a means of generating discrete grey-scale in real-time. A second integrated circuit design is also presented. This prototype neuraldetector backplane consists of a 4 x 4 array of optical-in, electronic-out processing units. These can sample the temporally multiplexed grey-scale generated by the SBS256. The neurons implement the post-synaptic summing and thresholding function, and can respond to both positive and negative activations - a requirement of many artificial neural network models.

Alpha matting is an important topic in areas of computer vision. It has various applications, such as virtual reality, digital image and video editing, and image synthesis. The conventional approaches for alpha matting perform unsatisfactorily when they encounter complicated background and foreground. It is also difficult for them to extract alpha matte accurately when the foreground objects are transparent, semi-transparent, perforated or hairy. Fortunately, the rapid development of deep learning techniques brings new possibilities for solving alpha matting problems. In this thesis, we propose a residual convolutional grid network for alpha matting, which is based on the convolutional neural networks (CNNs) and can learn the alpha matte directly from the original image and its trimap. Our grid network consists of horizontal residual convolutional computation blocks and vertical upsampling/downsampling convolutional computation blocks. By choosing different paths to pass information by itself, our network can not only retain the rich details of the image but also extract high-level abstract semantic information of the image. The experimental results demonstrate that our method can solve the matting problems that plague conventional matting methods for decades and outperform all the other state-of-the-art matting methods in quality and visual evaluation. The only matting method performs a little better than ours is the current best matting method. However, that matting method requires three times amount of trainable parameters compared with ours. Hence, our matting method is the best considering the computation complexity, memory usage, and matting performance.

With increasing demands on limited water resources and unavailability of suitable dam sites, it is essential that available storage works be carefully planned and efficiently operated to meet the present and future water needs.This research report presents an attempt to: i) use Artificial Neural Networks (ANN) for the simulation of the Crocodile water resource system located in the Mpumalanga province of South Africa and ii) use the model to assess to what extent Kwena dam, the only major dam in the system could meet the required 0.9m3/s cross border flow to Mozambique. The modelling was confined to the low flow periods when the Kwena dam releases are significant. The form of ANN model developed in this study is the standard error backpropagation run on a daily time scale. It is comprised of 32 inputs being four irrigation abstractions at Montrose, Tenbosch, Riverside and Karino; current and average daily rainfall totals for the previous 4 days at the respective rainfall stations; average daily temperature at Karino and Nelspruit; daily releases from Kwena dam; daily streamflow from the tributaries of Kaap, Elands and Sand rivers and the previous day’s flow at Tenbosch. The single output was the current day’s flow at Tenbosch. To investigate the extent to which the 0.9m3/s flow requirement into Mozambique could be met, data from a representative dry year and four release scenarios were used. The scenarios assumed that Kwena dam was 100%, 75%, 50% and 25% full at the beginning of the year. It was found as expected that increasing Kwena releases improved the cross border flows but the improvement in providing the 0.9m3/s cross border flow was minimal. For the scenario when the dam is initially full, the requirement was met with an improvement of 11% over the observed flows.

A feed forward architecture is suggested that increases the complexity of conventional neural network components through the implementation of a more complex scheme of interconnection. This is done with a view to increasing the range of application of the feed forward paradigm. The uniqueness of this new network design is illustrated by developing an extended taxonomy of accepted published constructs specific and similar to the higher order, product kernel approximations achievable using "parallel paths". Network topologies from this taxonomy are then compared to each other and the architectures containing parallel paths. In attempting this comparison, the context of the term "network topology" is reconsidered. The output of "channels" in these parallel paths are the products of a conventional connection as observed facilitating interconnection between two layers in a multilayered perceptron and the output of a network processing unit, a "control element", that can assume the identity of a number of pre-existing processing paradigms. The inherent property of universal approximation is tested by existence proof and the method found to be inconclusive. In so doing an argument is suggested to indicate that the parametric nature of the functions as determined by conditions upon initialization may only lead to conditional approximations. The property of universal approximation is neither, confirmed or denied. Universal approximation cannot be conclusively determined by the application of Stone Weierstrass Theorem, as adopted from real analysis. This novel implementation requires modifications to component concepts and the training algorithm. The inspiration for these modifications is related back to previously published work that also provides the basis of "proof of concept". By achieving proof of concept the appropriateness of considering network topology without assessing the impact of the method of training on this topology is considered and discussed in some detail. Results of limited testing are discussed with an emphasis on visualising component contributions to the global network output.

No description available.

Secret sharing is a fundamental notion for secure cryptographic design. In a secret sharing scheme, a set of participants shares a secret among them such that only pre-specified subsets of these shares can get together to recover the secret. This dissertation introduces a neural network approach to solve the problem of secret sharing for any given access structure. Other approaches have been used to solve this problem. However, the yet known approaches result in exponential increase in the amount of data that every participant need to keep. This amount is measured by the secret sharing scheme information rate. This work is intended to solve the problem with better information rate.

To obtain a suitable mathematical model of the input-output behavior of highly nonlinear, multi-scale, nonparametric phenomena, we introduce an adaptive radial basis function approximation approach. We use this approach to estimate the discrepancy between traditional model areas and the multiscale physics of systems involving distributed sensing and technology. Radial Basis Function Networks offers the possible approach to nonparametric multi-scale modeling for dynamical systems like the adaptive wing with the Synthetic Jet Actuator (SJA). We use the Regularized Orthogonal Least Square method (Mark, 1996) and the RAN-EKF (Resource Allocating Network-Extended Kalman Filter) as a reference approach. The first part of the algorithm determines the location of centers one by one until the error goal is met and regularization is achieved. The second process includes an algorithm for the adaptation of all the parameters in the Radial Basis Function Network, centers, variances (shapes) and weights. To demonstrate the effectiveness of these algorithms, SJA wind tunnel data are modeled using this approach. Good performance is obtained compared with conventional neural networks like the multi layer neural network and least square algorithm. Following this work, we establish Model Reference Adaptive Control (MRAC) formulations using an off-line Radial Basis Function Networks (RBFN). We introduce the adaptive control law using a RBFN. A theory that combines RBFN and adaptive control is demonstrated through the simple numerical simulation of the SJA wing. It is expected that these studies will provide a basis for achieving an intelligent control structure for future active wing aircraft.

The aim of this thesis is to describe how a statisticallybased neural network technology, here named BCPNN (BayesianConfidence Propagation Neural Network), which may be identifiedby rewriting Bayes' rule, can be used within a fewapplications, data mining and classification with credibilityintervals as well as unsupervised pattern recognition. BCPNN is a neural network model somewhat reminding aboutBayesian decision trees which are often used within artificialintelligence systems. It has previously been success- fullyapplied to classification tasks such as fault diagnosis,supervised pattern recognition, hiearchical clustering and alsoused as a model for cortical memory. The learning paradigm usedin BCPNN is rather different from many other neural networkarchitectures. The learning in, e.g. the popularbackpropagation (BP) network, is a gradient method on an errorsurface, but learning in BCPNN is based upon calculations ofmarginal and joint prob- abilities between attributes. This isa quite time efficient process compared to, for instance,gradient learning. The interpretation of the weight values inBCPNN is also easy compared to many other networkarchitechtures. The values of these weights and theiruncertainty is also what we are focusing on in our data miningapplication. The most important results and findings in thisthesis can be summarised in the following points:     We demonstrate how BCPNN (Bayesian Confidence PropagationNeural Network) can be extended to model the uncertainties incollected statistics to produce outcomes as distributionsfrom two different aspects: uncertainties induced by sparsesampling, which is useful for data mining; uncertainties dueto input data distributions, which is useful for processmodelling.     We indicate how classification with BCPNN gives highercertainty than an optimal Bayes classifier and betterprecision than a naïve Bayes classifier for limited datasets.     We show how these techniques have been turned into auseful tool for real world applications within the drugsafety area in particular.     We present a simple but working method for doingautomatic temporal segmentation of data sequences as well asindicate some aspects of temporal tasks for which a Bayesianneural network may be useful.     We present a method, based on recurrent BCPNN, whichperforms a similar task as an unsupervised clustering method,on a large database with noisy incomplete data, but muchquicker, with an efficiency in finding patterns comparablewith a well known (Autoclass) Bayesian clustering method,when we compare their performane on artificial data sets.Apart from BCPNN being able to deal with really large datasets, because it is a global method working on collectivestatistics, we also get good indications that the outcomefrom BCPNN seems to have higher clinical relevance thanAutoclass in our application on the WHO database of adversedrug reactions and therefore is a relevant data mining toolto use on the WHO database. Artificial neural network, Bayesian neural network, datamining, adverse drug reaction signalling, classification,learning.

No description available.