Learning with regularizers in multilayer neural networks

We study the effect of regularization in an on-line gradient-descent learning scenario for a general two-layer student network with an arbitrary number of hidden units. Training examples are randomly drawn input vectors labelled by a two-layer teacher network with an arbitrary number of hidden units which may be corrupted by Gaussian output noise. We examine the effect of weight decay regularization on the dynamical evolution of the order parameters and generalization error in various phases of the learning process, in both noiseless and noisy scenarios.

The role of biases in on-line learning of two-layer networks

The influence of biases on the learning dynamics of a two-layer neural network, a normalized soft-committee machine, is studied for on-line gradient descent learning. Within a statistical mechanics framework, numerical studies show that the inclusion of adjustable biases dramatically alters the learning dynamics found previously. The symmetric phase which has often been predominant in the original model all but disappears for a non-degenerate bias task. The extended model furthermore exhibits a much richer dynamical behavior, e.g. attractive suboptimal symmetric phases even for realizable cases and noiseless data.

Dynamics of on-line learning in radial basis function networks

On-line learning is examined for the radial basis function network, an important and practical type of neural network. The evolution of generalization error is calculated within a framework which allows the phenomena of the learning process, such as the specialization of the hidden units, to be analyzed. The distinct stages of training are elucidated, and the role of the learning rate described. The three most important stages of training, the symmetric phase, the symmetry-breaking phase, and the convergence phase, are analyzed in detail; the convergence phase analysis allows derivation of maximal and optimal learning rates. As well as finding the evolution of the mean system parameters, the variances of these parameters are derived and shown to be typically small. Finally, the analytic results are strongly confirmed by simulations.

On-line learning in radial basis functions networks

An analytic investigation of the average case learning and generalization properties of Radial Basis Function Networks (RBFs) is presented, utilising on-line gradient descent as the learning rule. The analytic method employed allows both the calculation of generalization error and the examination of the internal dynamics of the network. The generalization error and internal dynamics are then used to examine the role of the learning rate and the specialization of the hidden units, which gives insight into decreasing the time required for training. The realizable and over-realizable cases are studied in detail; the phase of learning in which the hidden units are unspecialized (symmetric phase) and the phase in which asymptotic convergence occurs are analyzed, and their typical properties found. Finally, simulations are performed which strongly confirm the analytic results.

Transients and asymptotics of natural gradient learning

We analyse natural gradient learning in a two-layer feed-forward neural network using a statistical mechanics framework which is appropriate for large input dimension. We find significant improvement over standard gradient descent in both the transient and asymptotic phases of learning.

Noise, regularizers, and unrealizable scenarios in online learning from restricted training sets

We study the dynamics of on-line learning in multilayer neural networks where training examples are sampled with repetition and where the number of examples scales with the number of network weights. The analysis is carried out using the dynamical replica method aimed at obtaining a closed set of coupled equations for a set of macroscopic variables from which both training and generalization errors can be calculated. We focus on scenarios whereby training examples are corrupted by additive Gaussian output noise and regularizers are introduced to improve the network performance. The dependence of the dynamics on the noise level, with and without regularizers, is examined, as well as that of the asymptotic values obtained for both training and generalization errors. We also demonstrate the ability of the method to approximate the learning dynamics in structurally unrealizable scenarios. The theoretical results show good agreement with those obtained by computer simulations.

A constructive learning algorithm based on back-propagation

There are been a resurgence of interest in the neural networks field in recent years, provoked in part by the discovery of the properties of multi-layer networks. This interest has in turn raised questions about the possibility of making neural network behaviour more adaptive by automating some of the processes involved. Prior to these particular questions, the process of determining the parameters and network architecture required to solve a given problem had been a time consuming activity. A number of researchers have attempted to address these issues by automating these processes, concentrating in particular on the dynamic selection of an appropriate network architecture.The work presented here specifically explores the area of automatic architecture selection; it focuses upon the design and implementation of a dynamic algorithm based on the Back-Propagation learning algorithm. The algorithm constructs a single hidden layer as the learning process proceeds using individual pattern error as the basis of unit insertion. This algorithm is applied to several problems of differing type and complexity and is found to produce near minimal architectures that are shown to have a high level of generalisation ability.

Negotiating regional futures:the successes and failures of the West Midlands Regional Development Agency Network

The introduction of Regional Development Agencies (RDAs) in the English regions in 1999 presented a new set of collaborative challenges to existing local institutions. The key objectives of the new policy impetus emphasise increased joined-up thinking and holistic regional governance. Partners were enjoined to promote cross-sector collaboration and present a coherent regional voice. This study aims to evaluate the impact of an RDA on the partnership infrastructure of the West Midlands. The RDA network incorporates a wide spectrum of interest and organisations with diverse collaborative histories, competencies and capacities. The study has followed partners through the process over an eighteen-month period and has sought to explore the complexities and tensions of partnership working 'on the ground'. A strong qualitative methodology has been employed in generating 'thick descriptions' of the policy domain. The research has probed beyond the 'rhetoric' of partnerships and explores the sensitivities of the collaboration process. A number of theoretical frameworks have been employed, including policy network theory; partnership and collaboration theory; organisational learning; and trust and social capital. The structural components of the West Midlands RDA network are explored, including the structural configuration of the network and stocks of human and social capital assets. These combine to form the asset base of the network. Three sets of network behaviours are then explored, namely, strategy, the management of perceptions, and learning. The thesis explores how the combination of assets and behaviours affect, and in turn are affected by, each other. The findings contribute to the growing body of knowledge and understanding surrounding policy networks and collaborative governance.

Finding structures in information networks using the affinity network

This thesis proposes a novel graphical model for inference called the Affinity Network,which displays the closeness between pairs of variables and is an alternative to Bayesian Networks and Dependency Networks. The Affinity Network shares some similarities with Bayesian Networks and Dependency Networks but avoids their heuristic and stochastic graph construction algorithms by using a message passing scheme. A comparison with the above two instances of graphical models is given for sparse discrete and continuous medical data and data taken from the UCI machine learning repository. The experimental study reveals that the Affinity Network graphs tend to be more accurate on the basis of an exhaustive search with the small datasets. Moreover, the graph construction algorithm is faster than the other two methods with huge datasets. The Affinity Network is also applied to data produced by a synchronised system. A detailed analysis and numerical investigation into this dynamical system is provided and it is shown that the Affinity Network can be used to characterise its emergent behaviour even in the presence of noise.

Learning to share knowledge in the Italian motorsport industry

The paper outlines a perspective on learning how to share knowledge in the context of inter-firm networks and highlights the essential role of participation in collaborative activities. This perspective suggests that knowledge sharing is not something achieved through the simple transfer of resources, but rather is an ongoing social accomplishment in which network firms constitute and re-constitute knowledge while engaging in collaborative activities. Empirical support for this view is offered by an in-depth and multiyear study of the development of collaborative relationships between a leading racing car manufacturer and its suppliers in the Italian motorsport industry. The study shows that knowledge is generated over time through the instigation of three knowledge sharing processes: the promotion of a culture of working together, co-location and the use of resident engineers, and shared education and training.

Analysis of constructivist, network-based discourses:concepts, prospects, and illustrations

The authors propose a new approach to discourse analysis which is based on meta data from social networking behavior of learners who are submerged in a socially constructivist e-learning environment. It is shown that traditional data modeling techniques can be combined with social network analysis - an approach that promises to yield new insights into the largely uncharted domain of network-based discourse analysis. The chapter is treated as a non-technical introduction and is illustrated with real examples, visual representations, and empirical findings. Within the setting of a constructivist statistics course, the chapter provides an illustration of what network-based discourse analysis is about (mainly from a methodological point of view), how it is implemented in practice, and why it is relevant for researchers and educators.

The importance of power dynamics in the development of asynchronous online learning communities

This research explored how a more student-directed learning design can support the creation of togetherness and belonging in a community of distance learners in formal higher education. Postgraduate students in a New Zealand School of Education experienced two different learning tasks as part of their online distance learning studies. The tasks centered around two online asynchronous discussions each for the same period of time and with the same group of students, but following two different learning design principles. All messages were analyzed using a twostep analysis process, content analysis and social network analysis. Although the findings showed a balance of power between the tutor and the students in the first high e-moderated activity, a better pattern of group interaction and community feeling was found in the low e-moderated activity. The paper will discuss the findings in terms of the implications for learning design and the role of the tutor.

A learning feed-forward current controller for linear reciprocating vapor compressors

Direct-drive linear reciprocating compressors offer numerous advantages over conventional counterparts which are usually driven by a rotary induction motor via a crank shaft. However, to ensure efficient and reliable operation under all conditions, it is essential that motor current of a linear compressor follows a sinusoidal current command with a frequency which matches the system resonant frequency. The design of a high-performance current controller for linear compressor drive presents a challenge since the system is highly nonlinear, and an effective solution must be low cost. In this paper, a learning feed-forward current controller for the linear compressors is proposed. It comprises a conventional feedback proportional-integral controller and a feed-forward B-spline neural network (BSNN). The feed-forward BSNN is trained online and in real time in order to minimize the current tracking error. Extensive simulation and experiment results with a prototype linear compressor show that the proposed current controller exhibits high steady state and transient performance. © 2009 IEEE.