Neural networks: A principled perspective

Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.

Neural networks: A principled perspective

Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.

Theoretical foundations of neural networks

Neural networks have often been motivated by superficial analogy with biological nervous systems. Recently, however, it has become widely recognised that the effective application of neural networks requires instead a deeper understanding of the theoretical foundations of these models. Insight into neural networks comes from a number of fields including statistical pattern recognition, computational learning theory, statistics, information geometry and statistical mechanics. As an illustration of the importance of understanding the theoretical basis for neural network models, we consider their application to the solution of multi-valued inverse problems. We show how a naive application of the standard least-squares approach can lead to very poor results, and how an appreciation of the underlying statistical goals of the modelling process allows the development of a more general and more powerful formalism which can tackle the problem of multi-modality.

Design and synthesis of novel hydrogels for biological applications

The aims of this project were:1) the synthesis of a range of new polyether-based vinylic monomers and their incorporation into poly(2-hydroxyethyl methacrylate) (poly(HEMA)) based hydrogel networks, of interest to the contact lens industry.2) the synthesis of a range of alkyltartronic acids, and their derivatives. These molecules may ultimately be used to produce functionalised poly(-hydroxy acids) of potential interest in either drug delivery or surgical suture applications. The novel syntheses of a range of both methoxy poly(ethylene glycol) acrylates (MPEGAs) and poly(ethylene glycol) acrylates (PEGAs) are described. Products were obtained in very good yields. These new polyether-based vinylic monomers were copolymerised with 2-hydroxyethyl methacrylate (HEMA) to produce a range of hydrogels. The equilibrium water contents (EWC) and surface properties of these copolymers containing linear polyethers were examined. It was found that the EWC was enhanced by the presence of the hydrophilic polyether chains.Results suggest that the polyether side chains express themselves at the polymer surface, thus dictating the surface properties of the gels. Consequentially, this leads to an advantageous reduction in the surface adhesion of biological species. A synthesis of a range of alkyltartronic acids is also described. The acids prepared were obtained in very good yields using a novel four-stage synthesis. These acids were modified to give potassium monoethyl alkyltartronates. Although no polyesterification is described in this thesis, these modified alkyltartronic acid derivatives are considered to be potentially excellent starting materials for poly (alkyltartronic acid) synthesis via anhydrocarboxylate or anhydrosulphite cyclic monomers.

A novel silicon membrane-based biosensing platform using distributive sensing strategy and artificial neural networks for feature analysis

A novel biosensing system based on a micromachined rectangular silicon membrane is proposed and investigated in this paper. A distributive sensing scheme is designed to monitor the dynamics of the sensing structure. An artificial neural network is used to process the measured data and to identify cell presence and density. Without specifying any particular bio-application, the investigation is mainly concentrated on the performance testing of this kind of biosensor as a general biosensing platform. The biosensing experiments on the microfabricated membranes involve seeding different cell densities onto the sensing surface of membrane, and measuring the corresponding dynamics information of each tested silicon membrane in the form of a series of frequency response functions (FRFs). All of those experiments are carried out in cell culture medium to simulate a practical working environment. The EA.hy 926 endothelial cell lines are chosen in this paper for the bio-experiments. The EA.hy 926 endothelial cell lines represent a particular class of biological particles that have irregular shapes, non-uniform density and uncertain growth behaviour, which are difficult to monitor using the traditional biosensors. The final predicted results reveal that the methodology of a neural-network based algorithm to perform the feature identification of cells from distributive sensory measurement has great potential in biosensing applications.

The application of methods of uncertain reasoning to the biological classification of river water quality

This thesis presents an investigation into the application of methods of uncertain reasoning to the biological classification of river water quality. Existing biological methods for reporting river water quality are critically evaluated, and the adoption of a discrete biological classification scheme advocated. Reasoning methods for managing uncertainty are explained, in which the Bayesian and Dempster-Shafer calculi are cited as primary numerical schemes. Elicitation of qualitative knowledge on benthic invertebrates is described. The specificity of benthic response to changes in water quality leads to the adoption of a sensor model of data interpretation, in which a reference set of taxa provide probabilistic support for the biological classes. The significance of sensor states, including that of absence, is shown. Novel techniques of directly eliciting the required uncertainty measures are presented. Bayesian and Dempster-Shafer calculi were used to combine the evidence provided by the sensors. The performance of these automatic classifiers was compared with the expert's own discrete classification of sampled sites. Variations of sensor data weighting, combination order and belief representation were examined for their effect on classification performance. The behaviour of the calculi under evidential conflict and alternative combination rules was investigated. Small variations in evidential weight and the inclusion of evidence from sensors absent from a sample improved classification performance of Bayesian belief and support for singleton hypotheses. For simple support, inclusion of absent evidence decreased classification rate. The performance of Dempster-Shafer classification using consonant belief functions was comparable to Bayesian and singleton belief. Recommendations are made for further work in biological classification using uncertain reasoning methods, including the combination of multiple-expert opinion, the use of Bayesian networks, and the integration of classification software within a decision support system for water quality assessment.

The application of artificial neural networks to the interpretation and classification of freshwater benthic invertebrate communities

This thesis presents a thorough and principled investigation into the application of artificial neural networks to the biological monitoring of freshwater. It contains original ideas on the classification and interpretation of benthic macroinvertebrates, and aims to demonstrate their superiority over the biotic systems currently used in the UK to report river water quality. The conceptual basis of a new biological classification system is described, and a full review and analysis of a number of river data sets is presented. The biological classification is compared to the common biotic systems using data from the Upper Trent catchment. This data contained 292 expertly classified invertebrate samples identified to mixed taxonomic levels. The neural network experimental work concentrates on the classification of the invertebrate samples into biological class, where only a subset of the sample is used to form the classification. Other experimentation is conducted into the identification of novel input samples, the classification of samples from different biotopes and the use of prior information in the neural network models. The biological classification is shown to provide an intuitive interpretation of a graphical representation, generated without reference to the class labels, of the Upper Trent data. The selection of key indicator taxa is considered using three different approaches; one novel, one from information theory and one from classical statistical methods. Good indicators of quality class based on these analyses are found to be in good agreement with those chosen by a domain expert. The change in information associated with different levels of identification and enumeration of taxa is quantified. The feasibility of using neural network classifiers and predictors to develop numeric criteria for the biological assessment of sediment contamination in the Great Lakes is also investigated.

Investigating the human mirror neuron system by means of cortical synchronization during the imitation of biological movements

The human mirror neuron system (MNS) has recently been a major topic of research in cognitive neuroscience. As a very basic reflection of the MNS, human observers are faster at imitating a biological as compared with a non-biological movement. However, it is unclear which cortical areas and their interactions (synchronization) are responsible for this behavioural advantage. We investigated the time course of long-range synchronization within cortical networks during an imitation task in 10 healthy participants by means of whole-head magnetoencephalography (MEG). Extending previous work, we conclude that left ventrolateral premotor, bilateral temporal and parietal areas mediate the observed behavioural advantage of biological movements in close interaction with the basal ganglia and other motor areas (cerebellum, sensorimotor cortex). Besides left ventrolateral premotor cortex, we identified the right temporal pole and the posterior parietal cortex as important junctions for the integration of information from different sources in imitation tasks that are controlled for movement (biological vs. non-biological) and that involve a certain amount of spatial orienting of attention. Finally, we also found the basal ganglia to participate at an early stage in the processing of biological movement, possibly by selecting suitable motor programs that match the stimulus.