Learning in neural networks and stochastic approximation methods with averaging

The problem of adjusting the weights (learning) in multilayer feedforward neural networks (NN) is known to be of a high importance when utilizing NN techniques in various practical applications. The learning procedure is to be performed as fast as possible and in a simple computational fashion, the two requirements which are usually not satisfied practically by the methods developed so far. Moreover, the presence of random inaccuracies are usually not taken into account. In view of these three issues, an alternative stochastic approximation approach discussed in the paper, seems to be very promising.

Moving feedback forward: theory to practice

There is substantial research interest in tutor feedback and students’ perception and use of such feedback. This paper considers some of the major issues raised in relation to tutor feedback and student learning. We explore some of the current feedback drivers, most notably the need for feedback to move away from simply a monologue from a tutor to a student to a valuable tutor–student dialogue. In relation to moving feedback forward the notions of self regulation, dialogue and social learning are explored and then considered in relation to how such theory can translate into practice. The paper proposes a framework (GOALS) as a tool through which tutors can move theory into practice with the aim of improving student learning from feedback.

A simple analysis of thermodynamic properties for classical plasmas: I. theory

By eliminating the short range negative divergence of the Debye–Hückel pair distribution function, but retaining the exponential charge screening known to operate at large interparticle separation, the thermodynamic properties of one-component plasmas of point ions or charged hard spheres can be well represented even in the strong coupling regime. Predicted electrostatic free energies agree within 5% of simulation data for typical Coulomb interactions up to a factor of 10 times the average kinetic energy. Here, this idea is extended to the general case of a uniform ionic mixture, comprising an arbitrary number of components, embedded in a rigid neutralizing background. The new theory is implemented in two ways: (i) by an unambiguous iterative algorithm that requires numerical methods and breaks the symmetry of cross correlation functions; and (ii) by invoking generalized matrix inverses that maintain symmetry and yield completely analytic solutions, but which are not uniquely determined. The extreme computational simplicity of the theory is attractive when considering applications to complex inhomogeneous fluids of charged particles.

Modular non-computational-connectionist-hybrid neural network approach to robotic systems

Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.

Inverse problems in neural field theory

We study inverse problems in neural field theory, i.e., the construction of synaptic weight kernels yielding a prescribed neural field dynamics. We address the issues of existence, uniqueness, and stability of solutions to the inverse problem for the Amari neural field equation as a special case, and prove that these problems are generally ill-posed. In order to construct solutions to the inverse problem, we first recast the Amari equation into a linear perceptron equation in an infinite-dimensional Banach or Hilbert space. In a second step, we construct sets of biorthogonal function systems allowing the approximation of synaptic weight kernels by a generalized Hebbian learning rule. Numerically, this construction is implemented by the Moore–Penrose pseudoinverse method. We demonstrate the instability of these solutions and use the Tikhonov regularization method for stabilization and to prevent numerical overfitting. We illustrate the stable construction of kernels by means of three instructive examples.

P-Prism: a computationally efficient approach to scaling up classification rule induction

Top Down Induction of Decision Trees (TDIDT) is the most commonly used method of constructing a model from a dataset in the form of classification rules to classify previously unseen data. Alternative algorithms have been developed such as the Prism algorithm. Prism constructs modular rules which produce qualitatively better rules than rules induced by TDIDT. However, along with the increasing size of databases, many existing rule learning algorithms have proved to be computational expensive on large datasets. To tackle the problem of scalability, parallel classification rule induction algorithms have been introduced. As TDIDT is the most popular classifier, even though there are strongly competitive alternative algorithms, most parallel approaches to inducing classification rules are based on TDIDT. In this paper we describe work on a distributed classifier that induces classification rules in a parallel manner based on Prism.

Bifurcations and state changes in the human alpha rhythm: Theory and experiment

Despite many decades investigating scalp recordable 8–13-Hz (alpha) electroencephalographic activity, no consensus has yet emerged regarding its physiological origins nor its functional role in cognition. Here we outline a detailed, physiologically meaningful, theory for the genesis of this rhythm that may provide important clues to its functional role. In particular we find that electroencephalographically plausible model dynamics, obtained with physiological admissible parameterisations, reveals a cortex perched on the brink of stability, which when perturbed gives rise to a range of unanticipated complex dynamics that include 40-Hz (gamma) activity. Preliminary experimental evidence, involving the detection of weak nonlinearity in resting EEG using an extension of the well-known surrogate data method, suggests that nonlinear (deterministic) dynamics are more likely to be associated with weakly damped alpha activity. Thus rather than the “alpha rhythm” being an idling rhythm it may be more profitable to conceive it as a readiness rhythm.

Home, meaning and identity: learning from the English model of shared ownership

This article explores the problematic nature of the label “home ownership” through a case study of the English model of shared ownership, one of the methods used by the UK government to make home ownership affordable. Adopting a legal and socio-legal analysis, the article considers whether shared ownership is capable of fulfilling the aspirations households have for home ownership. To do so, the article considers the financial and nonfinancial meanings attached to home ownership and suggests that the core expectation lies in ownership of the value. The article demonstrates that the rights and responsibilities of shared owners are different in many respects from those of traditional home owners, including their rights as regards ownership of the value. By examining home ownership through the lens of shared ownership the article draws out lessons of broader significance to housing studies. In particular, it is argued that shared ownership shows the limitations of two dichotomies commonly used in housing discourse: that between private and social housing; and the classification of tenure between owner-occupiers and renters. The article concludes that a much more nuanced way of referring to home ownership is required, and that there is a need for a change of expectations amongst consumers as to what sharing ownership means.

Implicit learning and imperceptible influence: Syncretic literacy of multilingual Chinese children.

This article reports on an ethnographic study involving the literacy practices of two multilingual Chinese children from two similar yet different cultural and linguistic contexts: Montreal and Singapore. Using syncretism as a theoretical tool, this inquiry examines how family environment and support facilitate children’s process of becoming literate in multiple languages. Informed by sociocultural theory, the inquiry looks in particular at the role of grandparents in the syncretic literacy practices of children. Through comparative analysis, the study reveals similarities and differences that, when considered together, contribute to our understanding of multilingual children’s creative forms of learning with regard to their rich literacy resources in multiple languages, the imperceptible influences of mediators, various learning styles and syncretic literacy practices.

The role of context in forming young learners' attitudes and motivation to learning French

Despite the wealth of valuable information that has been generated by motivation studies to date, there are certain limitations in the common approaches. Quantitative and psychometric approaches to motivation research that have dominated in recent decades provided epiphenomenal descriptions of learner motivation within different contexts. However, these approaches assume homogeneity within a given group and often mask the variation between learners within the same, and different, contexts. Although these studies have provided empirical data to form and validate theoretical constructs, they have failed to recognise learners as individual ‘people’ that interact with their context. Learning context has become increasingly explicit in motivation studies, (see Coleman et al. 2007 and Housen et al. 2011), however it is generally considered as a background variable which is pre-existing and external to the individual. Stemming from the recent ‘social turn’ (Block 2003) in SLA research from a more cognitive-linguistic perspective to a more context-specific view of language learning, there has been an upsurge in demand for a greater focus on the ‘person in context’ in motivation research (Ushioda 2011). This paper reports on the findings of a longitudinal study of young English learners of French as they transition from primary to secondary school. Over 12 months, the study employed a mixed-method approach in order to gain an in-depth understanding of how the learners’ context influenced attitudes to language learning. The questionnaire results show that whilst the learners displayed some consistent and stable motivational traits over the 12 months, there were significant differences for learners within different contexts in terms of their attitudes to the language classroom and their levels of self-confidence. A subsequent examination of the qualitative focus group data provided an insight into how and why these attitudes were formed and emphasised the dynamic and complex interplay between learners and their context.

Neural population models and cortical field theory: overview

The term neural population models (NPMs) is used here as catchall for a wide range of approaches that have been variously called neural mass models, mean field models, neural field models, bulk models, and so forth. All NPMs attempt to describe the collective action of neural assemblies directly. Some NPMs treat the densely populated tissue of cortex as an excitable medium, leading to spatially continuous cortical field theories (CFTs). An indirect approach would start by modelling individual cells and then would explain the collective action of a group of cells by coupling many individual models together. In contrast, NPMs employ collective state variables, typically defined as averages over the group of cells, in order to describe the population activity directly in a single model. The strength and the weakness of his approach are hence one and the same: simplification by bulk. Is this justified and indeed useful, or does it lead to oversimplification which fails to capture the pheno ...

Application of complex extreme learning machine to multiclass classification problems with high dimensionality: a THz spectra classification problem

We extend extreme learning machine (ELM) classifiers to complex Reproducing Kernel Hilbert Spaces (RKHS) where the input/output variables as well as the optimization variables are complex-valued. A new family of classifiers, called complex-valued ELM (CELM) suitable for complex-valued multiple-input–multiple-output processing is introduced. In the proposed method, the associated Lagrangian is computed using induced RKHS kernels, adopting a Wirtinger calculus approach formulated as a constrained optimization problem similarly to the conventional ELM classifier formulation. When training the CELM, the Karush–Khun–Tuker (KKT) theorem is used to solve the dual optimization problem that consists of satisfying simultaneously smallest training error as well as smallest norm of output weights criteria. The proposed formulation also addresses aspects of quaternary classification within a Clifford algebra context. For 2D complex-valued inputs, user-defined complex-coupled hyper-planes divide the classifier input space into four partitions. For 3D complex-valued inputs, the formulation generates three pairs of complex-coupled hyper-planes through orthogonal projections. The six hyper-planes then divide the 3D space into eight partitions. It is shown that the CELM problem formulation is equivalent to solving six real-valued ELM tasks, which are induced by projecting the chosen complex kernel across the different user-defined coordinate planes. A classification example of powdered samples on the basis of their terahertz spectral signatures is used to demonstrate the advantages of the CELM classifiers compared to their SVM counterparts. The proposed classifiers retain the advantages of their ELM counterparts, in that they can perform multiclass classification with lower computational complexity than SVM classifiers. Furthermore, because of their ability to perform classification tasks fast, the proposed formulations are of interest to real-time applications.

Temperament and self-based correlates of cooperative, competitive and individualistic learning preferences

People vary in the extent to which they prefer cooperative, competitive or individualistic achievement tasks. In the present research, we conducted two studies designed to investigate correlates and possible roots of these social interdependence orientations, namely approach and avoidance temperament, general self-efficacy, implicit theories of intelligence, and contingencies of self-worth based in others’ approval, competition, and academic competence. The results indicated that approach temperament, general self-efficacy, and incremental theory were positively, and entity theory was negatively related to cooperative preferences (|r| range from .11 to .41); approach temperament, general self-efficacy, competition contingencies, and academic competence contingencies were positively related to competitive preferences (|r| range from .16 to .46); and avoidance temperament, entity theory, competitive contingencies, and academic competence contingencies were positively related, and incremental theory was negatively related to individualistic preferences (|r| range from .09 to .15). The findings are discussed with regard to the meaning of each of the three social interdependence orientations, cultural differences among the observed relations, and implications for practicioners.