Bayesian inference and learning in Gaussian process state-space models with Particle MCMC

State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems. We present a fully Bayesian approach to inference and learning (i.e. state estimation and system identification) in nonlinear nonparametric state-space models. We place a Gaussian process prior over the state transition dynamics, resulting in a flexible model able to capture complex dynamical phenomena. To enable efficient inference, we marginalize over the transition dynamics function and, instead, infer directly the joint smoothing distribution using specially tailored Particle Markov Chain Monte Carlo samplers. Once a sample from the smoothing distribution is computed, the state transition predictive distribution can be formulated analytically. Our approach preserves the full nonparametric expressivity of the model and can make use of sparse Gaussian processes to greatly reduce computational complexity.

Determining of the delay time for a heating ventilating and air-conditioning plant using two weighted neural network approach

This paper presents an two weighted neural network approach to determine the delay time for a heating, ventilating and air-conditioning (HVAC) plan to respond to control actions. The two weighted neural network is a fully connected four-layer network. An acceleration technique was used to improve the General Delta Rule for the learning process. Experimental data for heating and cooling modes were used with both the two weighted neural network and a traditional mathematical method to determine the delay time. The results show that two weighted neural networks can be used effectively determining the delay time for AVAC systems.

Geometrical learning, descriptive geometry, and biomimetic pattern recognition

Studies on learning problems from geometry perspective have attracted an ever increasing attention in machine learning, leaded by achievements on information geometry. This paper proposes a different geometrical learning from the perspective of high-dimensional descriptive geometry. Geometrical properties of high-dimensional structures underlying a set of samples are learned via successive projections from the higher dimension to the lower dimension until two-dimensional Euclidean plane, under guidance of the established properties and theorems in high-dimensional descriptive geometry. Specifically, we introduce a hyper sausage like geometry shape for learning samples and provides a geometrical learning algorithm for specifying the hyper sausage shapes, which is then applied to biomimetic pattern recognition. Experimental results are presented to show that the proposed approach outperforms three types of support vector machines with either a three degree polynomial kernel or a radial basis function kernel, especially in the cases of high-dimensional samples of a finite size. (c) 2005 Elsevier B.V. All rights reserved.

Determining of the delay time for a heating ventilating and air-conditioning plant using multi-weights neurons approach

This paper presents an multi weights neurons approach to determine the delay time for a Heating ventilating and air-conditioning (HVAC) plan to respond to control actions. The multi weights neurons is a fully connected four-layer network. An acceleration technique was used to improve the general delta rule for the learning process. Experimental data for heating and cooling modes were used with both the multi weights neurons and a traditional mathematical method to determine the delay time. The results show that multi weights neurons can be used effectively determining the delay time for HVAC systems.

Sparse Representations for Fast, One-Shot Learning

Humans rapidly and reliably learn many kinds of regularities and generalizations. We propose a novel model of fast learning that exploits the properties of sparse representations and the constraints imposed by a plausible hardware mechanism. To demonstrate our approach we describe a computational model of acquisition in the domain of morphophonology. We encapsulate phonological information as bidirectional boolean constraint relations operating on the classical linguistic representations of speech sounds in term of distinctive features. The performance model is described as a hardware mechanism that incrementally enforces the constraints. Phonological behavior arises from the action of this mechanism. Constraints are induced from a corpus of common English nouns and verbs. The induction algorithm compiles the corpus into increasingly sophisticated constraints. The algorithm yields one-shot learning from a few examples. Our model has been implemented as a computer program. The program exhibits phonological behavior similar to that of young children. As a bonus the constraints that are acquired can be interpreted as classical linguistic rules.

Learning and Example Selection for Object and Pattern Detection

This thesis presents a learning based approach for detecting classes of objects and patterns with variable image appearance but highly predictable image boundaries. It consists of two parts. In part one, we introduce our object and pattern detection approach using a concrete human face detection example. The approach first builds a distribution-based model of the target pattern class in an appropriate feature space to describe the target's variable image appearance. It then learns from examples a similarity measure for matching new patterns against the distribution-based target model. The approach makes few assumptions about the target pattern class and should therefore be fairly general, as long as the target class has predictable image boundaries. Because our object and pattern detection approach is very much learning-based, how well a system eventually performs depends heavily on the quality of training examples it receives. The second part of this thesis looks at how one can select high quality examples for function approximation learning tasks. We propose an {em active learning} formulation for function approximation, and show for three specific approximation function classes, that the active example selection strategy learns its target with fewer data samples than random sampling. We then simplify the original active learning formulation, and show how it leads to a tractable example selection paradigm, suitable for use in many object and pattern detection problems.

Roles of Knowledge in Motor Learning

The goal of this thesis is to apply the computational approach to motor learning, i.e., describe the constraints that enable performance improvement with experience and also the constraints that must be satisfied by a motor learning system, describe what is being computed in order to achieve learning, and why it is being computed. The particular tasks used to assess motor learning are loaded and unloaded free arm movement, and the thesis includes work on rigid body load estimation, arm model estimation, optimal filtering for model parameter estimation, and trajectory learning from practice. Learning algorithms have been developed and implemented in the context of robot arm control. The thesis demonstrates some of the roles of knowledge in learning. Powerful generalizations can be made on the basis of knowledge of system structure, as is demonstrated in the load and arm model estimation algorithms. Improving the performance of parameter estimation algorithms used in learning involves knowledge of the measurement noise characteristics, as is shown in the derivation of optimal filters. Using trajectory errors to correct commands requires knowledge of how command errors are transformed into performance errors, i.e., an accurate model of the dynamics of the controlled system, as is demonstrated in the trajectory learning work. The performance demonstrated by the algorithms developed in this thesis should be compared with algorithms that use less knowledge, such as table based schemes to learn arm dynamics, previous single trajectory learning algorithms, and much of traditional adaptive control.

Learning from patterns during information technology configuration.

This paper asks how people can be assisted in learning from practice, as a basis for informing future action, when configuring information technology (IT) in organizations. It discusses the use of Alexanderian Patterns as a means of aiding such learning. Three patterns are presented that have been derived from a longitudinal empirical study that has focused on practices surrounding IT configuration. The paper goes on to argue that Alexanderian Patterns offer a valuable means of learning from past experience. It is argued that learning from experience is an important dimension of deciding “what needs to be done” in configuring IT with organizational context. The three patterns outlined are described in some detail, and the implications of each discussed. Although it is argued that patterns, per se, provide a valuable tool for learning from experience, some potential dangers in seeking to codify experience with a patterns approach are also discussed.

Exploring the contribution of workplace learning to an HRD strategy in the Scottish legal profession.

Purpose – The purpose of this paper is to explore the relevance of human resource development (HRD) for law firms in the UK. It examines how the characteristics of legal professional practice in the UK, including the partnership structure, long established methods of targeting solicitors and the law society, may act as barriers to the implementation of HRD. Design/methodology/approach – The paper uses an exploratory case study research approach to investigate characteristics and issues influencing the adoption of HRD in a Scottish legal firm. Primary data are collected via semi-structured interviews with a cross-section of representatives. Findings – Despite recognition of the importance of learning, the characteristic elements of law firms, including the partnership structure; the pervasiveness of time-billed targets in the solicitor community; and HR’s profile and acceptance among the solicitor community, remain as barriers to the applicability of HRD. The research also exposes variability on the level and scope of development opportunities, an emphasis on technical skills development, and a lack of solicitors’ self-managed learning ability. Research limitations/implications – While the research findings provide a useful insight into the barriers to HRD in one legal firm, this does not allow for any generalisations being drawn from the study. Practical implications – The paper explores the suitability of workplace learning to support legal professional development. Originality/value – There is a dearth of research into HRD in legal practices in the UK. The paper contributes to the contextual influences that limit the applicability of HRD to legal professional practices.

Freedom to learn: a radically revised pedagogy to facilitate lifewide learning in the academic curriculum.

Higher education has progressed fairly steadily to a common pedagogical approach which centres on the idea of alignment. In this arrangement, intended learning outcomes are identified and declared; learning activities which will enable the desired learning and development to be achieved are conceived and undertaken with the support of appropriate and effective teaching; and assessment which calls for these outcomes is (ideally) carefully designed and implemented. All three elements are aligned in advance. The same principles and practices underpinned by notions of alignment have been applied to date in most of the purposeful schemes for personal development planning. In this chapter I argue that lifewide learning, wherein learning and development often occur incidentally in multiple and varied real-world situations throughout an individual’s life course, calls for a different approach, and a different pedagogy. Higher education should therefore visualise lifewide learning as an emergent phenomenon wherein the outcomes of learning emerge later on, and are often unintended. Consequently, they cannot be defined in advance of the activities through which they are formed. The main purpose of this chapter is to offer some practical ideas to support the development of pedagogies that would enable programme designers to embed in their programmes the principle and practice of lifewide education.

Developing a Pedagogy for Interactive Learning.

Recent developments in higher education have seen the demise of much didactic, teacher-directed instruction which was aimed mainly towards lower-level educational objectives. This traditional educational approach has been largely replaced by methods which feature the teacher as an originator or facilitator of interactive and learner-centred learning - with higher-level aims in mind. The origins of, and need for, these changes are outlined, leading into an account of the emerging pedagogical approach to interactive learning, featuring facilitation and reflection. Some of the main challenges yet to be confronted effectively in consolidating a sound and comprehensive pedagogical approach to interactive development of higher level educational aims are outlined.

Reflections on the development of a dynamic learning, teaching and assessment strategy.

Developing learning, teaching and assessment strategies that foster ongoing engagement and provide inspiration to academic staff is a particular challenge. This paper demonstrates how an institutional learning, teaching and assessment strategy was developed and a ‘dynamic’ strategy created in order to achieve the ongoing enhancement of the quality of the student learning experience. The authors use the discussion of the evolution, development and launch of the Strategy and underpinning Resource Bank to reflect on the hopes and intentions behind the approach; firstly the paper will discuss the collaborative and iterative approach taken to the development of an institutional learning, teaching and assessment strategy; and secondly, the development of open access educational resources to underpin the strategy. The paper then outlines staff engagement with the resource bank and positive outcomes which have been identified to date, identifies the next steps in achieving the ambition behind the strategy and outlines the action research and fuller evaluation which will be used to monitor progress and ensure responsive learning at institutional level.

How to run successful e-internships: a case for organizational learning.

Purpose – The purpose of this paper is to outline unique learning experience that virtual/e-internships can offer small and medium-sized enterprises and start-up organizations. Design/methodology/approach – We interviewed 18 experts on e-internships (interns and managers of internships) across several countries to learn more about the learning experiences for both organizations and interns. The information from these interviews was also used to formulate a number of recommendations. Findings – The interviews provided insights into how e-internships can provide development opportunities for interns, managers and staff within these organizations. One important benefit pertains to the skill development of both interns and managers. The interns get unique working experiences that also benefit the organizations in terms of their creativity, input and feedback. In return, managers get a unique learning experience that helps them expand their project management skills, interpersonal skills and mentoring. Practical implications – We outline a number of recommendations that consider skill development, the benefit of diversity in numerous forms as well as mutual benefits for enterprises and start-ups. Originality/value – The discussion of the various benefits and conditions under which virtual internships will succeed in organizations provide practitioners an insight into the organizational opportunities available to them given the right investment into e-interns and internship schemes.

Using an Outdoor Learning Space to Teach Sustainability and Material Processes in HE product Design.

The world is facing environmental changes that are increasingly affecting how we think about manufacturing, the consumption of products and use of resources. Within the HE product design community, thinking and designing sustainability’ has evolved to become a natural part of the curriculum. Paradoxical as the rise in awareness of sustainability increases there is growing concern within HE product design of the loss of workshop facilities and as a consequence a demise in teaching traditional object-making skills and material experimentation. We suggest the loss of workshops and tangible ‘learning by making skills’ also creates a lost opportunity for a rich learning resource to address sustainable thinking, design and manufacture ‘praxis’ within HE design education. Furthermore, as learning spaces are frequently discussed in design research, there seems to be little focus on how the use of an outdoor environment might influence learning outcomes particularly with regard to material teaching and sustainability. This 'case study' of two jewellery workshops, used outdoor learning spaces to explore both its impact on learning outcomes and to introduce some key principles of sustainable working methodologies and practices. Academics and students mainly from Norway and Scotland collaborated on this international research project. Participants made models from disposable packaging materials, which were cast in tin, in the sand on a local beach, using found timber to create a heat source for melting the metal. This approach of using traditional making skills, materials and nature was found to be a relevant contribution to a sustainable discourse.

Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics

Meng, Q., & Lee, M. (2005). Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics. Wermter, S., Palm, G., & Elshaw, M. (Eds.), In: Biomimetic Neural Learning for Intelligent Robots: Intelligent Systems, Cognitive Robotics, and Neuroscience. (pp. 315-332). (Lecture Notes in Computer Science). Springer Berlin Heidelberg.