Dynamics of on-line gradient descent learning for multilayer neural networks

We consider the problem of on-line gradient descent learning for general two-layer neural networks. An analytic solution is presented and used to investigate the role of the learning rate in controlling the evolution and convergence of the learning process.

Learning with noise and regularizers in multilayer neural networks

We study the effect of two types of noise, data noise and model noise, in an on-line gradient-descent learning scenario for general two-layer student network with an arbitrary number of hidden units. Training examples are randomly drawn input vectors labeled by a two-layer teacher network with an arbitrary number of hidden units. Data is then corrupted by Gaussian noise affecting either the output or the model itself. We examine the effect of both types of noise on the evolution of order parameters and the generalization error in various phases of the learning process.

Finite-size effects in on-line learning of multilayer neural networks

We complement recent advances in thermodynamic limit analyses of mean on-line gradient descent learning dynamics in multi-layer networks by calculating fluctuations possessed by finite dimensional systems. Fluctuations from the mean dynamics are largest at the onset of specialisation as student hidden unit weight vectors begin to imitate specific teacher vectors, increasing with the degree of symmetry of the initial conditions. In light of this, we include a term to stimulate asymmetry in the learning process, which typically also leads to a significant decrease in training time.

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.

Globally optimal on-line learning rules for multi-layer neural networks

We present a method for determining the globally optimal on-line learning rule for a soft committee machine under a statistical mechanics framework. This rule maximizes the total reduction in generalization error over the whole learning process. A simple example demonstrates that the locally optimal rule, which maximizes the rate of decrease in generalization error, may perform poorly in comparison.

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.

Globally optimal on-line learning rules

We present a method for determining the globally optimal on-line learning rule for a soft committee machine under a statistical mechanics framework. This work complements previous results on locally optimal rules, where only the rate of change in generalization error was considered. We maximize the total reduction in generalization error over the whole learning process and show how the resulting rule can significantly outperform the locally optimal rule.

The theory of on-line learning: a statistical physics approach

In this paper we review recent theoretical approaches for analysing the dynamics of on-line learning in multilayer neural networks using methods adopted from statistical physics. The analysis is based on monitoring a set of macroscopic variables from which the generalisation error can be calculated. A closed set of dynamical equations for the macroscopic variables is derived analytically and solved numerically. The theoretical framework is then employed for defining optimal learning parameters and for analysing the incorporation of second order information into the learning process using natural gradient descent and matrix-momentum based methods. We will also briefly explain an extension of the original framework for analysing the case where training examples are sampled with repetition.

Policy into practice:a study of public policy implementation and the role of learning

Public policy becomes managerial practice through a process of implementation. There is an established literature within Implementation Studies which explains the variables and some of the processes involved in implementation, but less attention has been focused upon how public service managers convert new policy initiatives into practice. The research proposes that managers and their organisations have to go through a process of learning in order to achieve the implementation of public policy. Data was collected over a five year period from four case studies of capital investment appraisal in the British National Health Service. Further data was collected from taped interviews by key actors within the case studies. The findings suggest that managers do learn to implement policy and four factors are important in this learning process. These are; (i) the nature of bureaucratic responsibility; (ii) the motivation of actors towards learning; (iii) the passage of time which allows for the development of competence and (iv) the use of project team structures. The research has demonstrated that the conversion of policy into practice occurs through the operationalisation of solutions to policy problems via job tasks. As such it suggests that in understanding how policy is implemented, technical learning is more important than cultural learning, in this context. In conclusion, a "Model of Learned Implementation" is presented, together with a discussion of some of the implications of the research. These are the possible use of more pilot projects for new policy initiatives and the more systematic diffusion of knowledge about implementation solutions.

Organisational learning - a critical systems thinking discipline

Original Paper European Journal of Information Systems (2001) 10, 135–146; doi:10.1057/palgrave.ejis.3000394 Organisational learning—a critical systems thinking discipline P Panagiotidis1,3 and J S Edwards2,4 1Deloitte and Touche, Athens, Greece 2Aston Business School, Aston University, Aston Triangle, Birmingham, B4 7ET, UK Correspondence: Dr J S Edwards, Aston Business School, Aston University, Aston Triangle, Birmingham, B4 7ET, UK. E-mail: j.s.edwards@aston.ac.uk 3Petros Panagiotidis is Manager responsible for the Process and Systems Integrity Services of Deloitte and Touche in Athens, Greece. He has a BSc in Business Administration and an MSc in Management Information Systems from Western International University, Phoenix, Arizona, USA; an MSc in Business Systems Analysis and Design from City University, London, UK; and a PhD degree from Aston University, Birmingham, UK. His doctorate was in Business Systems Analysis and Design. His principal interests now are in the ERP/DSS field, where he serves as project leader and project risk managment leader in the implementation of SAP and JD Edwards/Cognos in various major clients in the telecommunications and manufacturing sectors. In addition, he is responsible for the development and application of knowledge management systems and activity-based costing systems. 4John S Edwards is Senior Lecturer in Operational Research and Systems at Aston Business School, Birmingham, UK. He holds MA and PhD degrees (in mathematics and operational research respectively) from Cambridge University. His principal research interests are in knowledge management and decision support, especially methods and processes for system development. He has written more than 30 research papers on these topics, and two books, Building Knowledge-based Systems and Decision Making with Computers, both published by Pitman. Current research work includes the effect of scale of operations on knowledge management, interfacing expert systems with simulation models, process modelling in law and legal services, and a study of the use of artifical intelligence techniques in management accounting. Top of pageAbstract This paper deals with the application of critical systems thinking in the domain of organisational learning and knowledge management. Its viewpoint is that deep organisational learning only takes place when the business systems' stakeholders reflect on their actions and thus inquire about their purpose(s) in relation to the business system and the other stakeholders they perceive to exist. This is done by reflecting both on the sources of motivation and/or deception that are contained in their purpose, and also on the sources of collective motivation and/or deception that are contained in the business system's purpose. The development of an organisational information system that captures, manages and institutionalises meaningful information—a knowledge management system—cannot be separated from organisational learning practices, since it should be the result of these very practices. Although Senge's five disciplines provide a useful starting-point in looking at organisational learning, we argue for a critical systems approach, instead of an uncritical Systems Dynamics one that concentrates only on the organisational learning practices. We proceed to outline a methodology called Business Systems Purpose Analysis (BSPA) that offers a participatory structure for team and organisational learning, upon which the stakeholders can take legitimate action that is based on the force of the better argument. In addition, the organisational learning process in BSPA leads to the development of an intrinsically motivated information organisational system that allows for the institutionalisation of the learning process itself in the form of an organisational knowledge management system. This could be a specific application, or something as wide-ranging as an Enterprise Resource Planning (ERP) implementation. Examples of the use of BSPA in two ERP implementations are presented.

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.

A study in Britain and France of the development of cross-cultural in-house sales training using distance learning.

The thesis is concerned with cross-cultural distance learning in two countries: Great Britain and France. Taking the example of in-house sales training, it argues that it is possible to develop courses for use in two or more countries of differing culture and language. Two courses were developed by the researcher. Both were essentially print-based distance-learning courses designed to help salespeople achieve a better understanding of their customers. One used a quantitative, the other qualitative approach. One considered the concept of the return on investment and the other, for which a video support was also developed, considered the analysis of a customer's needs. Part 1 of the thesis considers differences in the training context between France and Britain followed by a review of the learning process with reference to distance learning. Part 2 looks at the choice of training medium course design and evaluation and sets out the methodology adopted, including problems encountered in this type of fieldwork. Part 3 analyses the data and draws conclusions from the findings, before offering a series of guidelines for those concerned with the development of cross-cultural in-house training courses. The results of the field tests on the two courses were analysed in relation to the socio-cultural, educational and experiential background of the learners as well as their preferred learning styles. The thesis argues that it is possible to develop effective in-house sales training courses to be used in two cultures and identifies key considerations which need to be taken into account when carrying out this type of work.

Does reviewing lead to better learning and decision making? Answers from a randomized stock market experiment

Background - The literature is not univocal about the effects of Peer Review (PR) within the context of constructivist learning. Due to the predominant focus on using PR as an assessment tool, rather than a constructivist learning activity, and because most studies implicitly assume that the benefits of PR are limited to the reviewee, little is known about the effects upon students who are required to review their peers. Much of the theoretical debate in the literature is focused on explaining how and why constructivist learning is beneficial. At the same time these discussions are marked by an underlying presupposition of a causal relationship between reviewing and deep learning. Objectives - The purpose of the study is to investigate whether the writing of PR feedback causes students to benefit in terms of: perceived utility about statistics, actual use of statistics, better understanding of statistical concepts and associated methods, changed attitudes towards market risks, and outcomes of decisions that were made. Methods - We conducted a randomized experiment, assigning students randomly to receive PR or non–PR treatments and used two cohorts with a different time span. The paper discusses the experimental design and all the software components that we used to support the learning process: Reproducible Computing technology which allows students to reproduce or re–use statistical results from peers, Collaborative PR, and an AI–enhanced Stock Market Engine. Results - The results establish that the writing of PR feedback messages causes students to experience benefits in terms of Behavior, Non–Rote Learning, and Attitudes, provided the sequence of PR activities are maintained for a period that is sufficiently long.

Small business development and the “learning organisation”

The paper proffers a tentative conceptualisation of the “small business strategic learning process”, demonstrating the complexity of the small firm learning and management task. The framework, built upon personal construct theory and learning theories, is elaborated through the grounding of relevant areas of the strategic management literature in an understanding of the distinctive managerial and behavioural features of the small business. The framework is then utilised to underpin consideration of the concepts of “organisational learning” and the “learning organisation” within a small firm developmental context. It is suggested that whilst organisational learning may be a key and effective small business management approach to underpin sustainable development, the learning organisation, as currently conceived in the mainstream literature, fails to recognise and address the idiosyncrasies, problems and constraints relating to sustainable small business development. There does appear, however, to be great potential for extending understanding of the learning organisation concept into the small business context. An indicative research agenda is suggested.

Learning from openness : the dynamics of breadth in external innovation linkages

We explore how openness in terms of external linkages generates learning effects, which enable firms to generate more innovation outputs from any given breadth of external linkages. Openness to external knowledge sources, whether through search activity or linkages to external partners in new product development, involves a process of interaction and information processing. Such activities are likely to be subject to a learning process, as firms learn which knowledge sources and collaborative linkages are most useful to their particular needs, and which partnerships are most effective in delivering innovation performance. Using panel data from Irish manufacturing plants, we find evidence of such learning effects: establishments with substantial experience of external collaborations in previous periods derive more innovation output from openness in the current period. © 2013 The Authors. Strategic Management Journal published by John Wiley & Sons Ltd.