Applicability of Statistical Learning Algorithms for Spatial Variability of Rock Depth

Two algorithms are outlined, each of which has interesting features for modeling of spatial variability of rock depth. In this paper, reduced level of rock at Bangalore, India, is arrived from the 652 boreholes data in the area covering 220 sqa <.km. Support vector machine (SVM) and relevance vector machine (RVM) have been utilized to predict the reduced level of rock in the subsurface of Bangalore and to study the spatial variability of the rock depth. The support vector machine (SVM) that is firmly based on the theory of statistical learning theory uses regression technique by introducing epsilon-insensitive loss function has been adopted. RVM is a probabilistic model similar to the widespread SVM, but where the training takes place in a Bayesian framework. Prediction results show the ability of learning machine to build accurate models for spatial variability of rock depth with strong predictive capabilities. The paper also highlights the capability ofRVM over the SVM model.

Machine learning modelling for predicting soil liquefaction susceptibility

This study describes two machine learning techniques applied to predict liquefaction susceptibility of soil based on the standard penetration test (SPT) data from the 1999 Chi-Chi, Taiwan earthquake. The first machine learning technique which uses Artificial Neural Network (ANN) based on multi-layer perceptions (MLP) that are trained with Levenberg-Marquardt backpropagation algorithm. The second machine learning technique uses the Support Vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses classification technique. ANN and SVM have been developed to predict liquefaction susceptibility using corrected SPT (N-1)(60)] and cyclic stress ratio (CSR). Further, an attempt has been made to simplify the models, requiring only the two parameters (N-1)(60) and peck ground acceleration (a(max)/g)], for the prediction of liquefaction susceptibility. The developed ANN and SVM models have also been applied to different case histories available globally. The paper also highlights the capability of the SVM over the ANN models.

Case study: Opening up opportunities for learning with digital technologies

Case study on Lewisham Southwark College and how they are encouraging students and staff to engage with a wide range of technologies to develop their digital confidence and capability.

Knowledge based strategy: appraising knowledge creation capability in organisations.

This thesis sets out a journey which culminates in the development of an analytical framework, the "Organisational Creativity Appraisal" which is intended to assist organisations in evaluating their ability to support and develop creativity. This framework is derived from the common thread of the thesis, which is drawn from a range of research and consultancy projects, and the resulting published work, spanning an eight year period, centring on the role of knowledge and creativity in the strategy and performance of organisations. The literature of strategy, learning and creativity increasingly recognises that organisational context is critical to the formation of strategy, to the content of the strategy and to its successful implementation. The thesis explores the ways in which learning and creativity, the basis of knowledge-based strategy, are influenced by organisational context or social architecture. The research explores the ways in which managers can gain greater understanding of the social architectures of their organisations so as to assist in supporting their strategic development. The central core of the thesis is the nine published papers upon which it is based but it also derives from the broader perspective of my published work in the form of both articles and books. The thesis further draws upon my own experience as a leader and manager in the context of university business schools and as a consultant, researcher and developer in the context of a range of international private and public sector organisations. The work is based upon a premise that theory should inform practice and that practice should inform theory. The "Organisational Creativity Appraisal" framework is informed by both theory and practice and is intended to assist in management practice. There is no assumption that management research can arrive at prescriptions for managerial and organisational behaviour. On the other hand management research can usefully inform management and organisational behaviour, as long as it is employed in a critically reflective manner. The "Organisational Creativity Appraisal" presented in this work should be regarded as the framework in its present form which is likely to develop further as my research progresses in the future.

Model Selection Methodology in Supervised Learning with Evolutionary Computation

Rowland, J.J. (2003) Model Selection Methodology in Supervised Learning with Evolutionary Computation. BioSystems 72, 1-2, pp 187-196, Nov

Fast automatic two-stage nonlinear model identification based on the extreme learning machine

It is convenient and effective to solve nonlinear problems with a model that has a linear-in-the-parameters (LITP) structure. However, the nonlinear parameters (e.g. the width of Gaussian function) of each model term needs to be pre-determined either from expert experience or through exhaustive search. An alternative approach is to optimize them by a gradient-based technique (e.g. Newton’s method). Unfortunately, all of these methods still need a lot of computations. Recently, the extreme learning machine (ELM) has shown its advantages in terms of fast learning from data, but the sparsity of the constructed model cannot be guaranteed. This paper proposes a novel algorithm for automatic construction of a nonlinear system model based on the extreme learning machine. This is achieved by effectively integrating the ELM and leave-one-out (LOO) cross validation with our two-stage stepwise construction procedure [1]. The main objective is to improve the compactness and generalization capability of the model constructed by the ELM method. Numerical analysis shows that the proposed algorithm only involves about half of the computation of orthogonal least squares (OLS) based method. Simulation examples are included to confirm the efficacy and superiority of the proposed technique.

A multi-output two-stage locally regularized model construction method using the extreme learning machine

This paper investigates the construction of linear-in-the-parameters (LITP) models for multi-output regression problems. Most existing stepwise forward algorithms choose the regressor terms one by one, each time maximizing the model error reduction ratio. The drawback is that such procedures cannot guarantee a sparse model, especially under highly noisy learning conditions. The main objective of this paper is to improve the sparsity and generalization capability of a model for multi-output regression problems, while reducing the computational complexity. This is achieved by proposing a novel multi-output two-stage locally regularized model construction (MTLRMC) method using the extreme learning machine (ELM). In this new algorithm, the nonlinear parameters in each term, such as the width of the Gaussian function and the power of a polynomial term, are firstly determined by the ELM. An initial multi-output LITP model is then generated according to the termination criteria in the first stage. The significance of each selected regressor is checked and the insignificant ones are replaced at the second stage. The proposed method can produce an optimized compact model by using the regularized parameters. Further, to reduce the computational complexity, a proper regression context is used to allow fast implementation of the proposed method. Simulation results confirm the effectiveness of the proposed technique. © 2013 Elsevier B.V.

Technological Learning in Developing Countries

Technological learning refers to the learning processes involved in improving the productive capabilities of an enterprise, sector or economy to enable it to produce higher quality goods or services with increasing levels of efficiency. Approaches to the study of technological learning include case studies of particular countries, sectors and firms; measures of export sophistication; and composite indicators of innovation and competitiveness. The present review draws on these approaches to provide an overview of the policies and practices that have been successful in different regions (East-Asia and Latin America) ; contexts (import substitution and liberalization) ; sectors (pulp and paper, IT services, electronics and passenger cars); and firms (Embrear and Lenovo). While it is clear that there is strong complementarity between domestic technological capability and the ability to absorb foreign technology, there is no simple policy recipe which is appropriate for all times, industries or places. Technological learning builds on and is shaped by what is already known. It requires time, space and resources all of which are influenced by the wider domestic and international context. The current international context is challenging but countries and firms have to find ways of moving forward despite the limited strategy space.

Developing management capability within a horizontal supply chain in performance measurement deployment and evolution: A Dynamic Capabilities and Goal Theory perspective

Complex collaboration in rapidly changing business environments create challenges for management capability in Utility Horizontal Supply Chains (UHSCs) involving the deploying and evolving of performance measures. The aim of the study is twofold. First, there is a need to explore how management capability can be developed and used to deploy and evolve Performance Measurement (PM), both across a UHSC and within its constituent organisations, drawing upon a theoretical nexus of Dynamic Capability (DC) theory and complementary Goal Theory. Second, to make a contribution to knowledge by empirically building theory using these constructs to show the management motivations and behaviours within PM-based DCs. The methodology uses an interpretive theory building, multiple case based approach (n=3) as part of a USHC. The data collection methods include, interviews (n=54), focus groups (n=10), document analysis and participant observation (reflective learning logs) over a five-year period giving longitudinal data. The empirical findings lead to the development of a conceptual framework showing that management capabilities in driving PM deployment and evolution can be represented as multilevel renewal and incremental Dynamic Capabilities, which can be further understood in terms of motivation and behaviour by Goal-Theoretic constructs. In addition three interrelated cross cutting themes of management capabilities in consensus building, goal setting and resource change were identified. These management capabilities require carefully planned development and nurturing within the UHSC. 

Learning outcomes tracking system (L.O.T.S):seeing student progress as term progresses

At QUB we have constructed a system that allows students to self-assess their capability on the fine grained learning outcomes for a module and to update their record as the term progresses. In the system each of the learning outcomes are linked to the relevant teaching session (lectures and labs) and to [online] resources that students can access at any time. Students can structure their own learning experience to their needs to attain the learning outcomes. The system keeps a history of the student’s record, allowing the lecturer to observe how the students’ abilities progress over the term and to compare it to assessment results. The system also keeps of any of the resource links that student has clicked on.

Machine learning methods for quantitative structure-property relationship modeling

Tese de doutoramento, Informática (Bioinformática), Universidade de Lisboa, Faculdade de Ciências, 2014

An exploratory study of how a Korean chaebol’s learning culture facilitates customer service

This paper explains how the organizational learning concept is used by managers in a global Korean company to promote group work, information sharing and an open communication style in order to produce a high level of customer service. Previously collected data from a set of in-depth personal interviews undertaken with three senior managers in a Korean electronics company were analyzed and interpreted using the grounded theory approach, and a number of propositions are put forward. The research findings show that managers in a chaebol deploy organizational learning to identify skilled and knowledgeable staff, and improve the organization’s capability by placing emphasis on developing harmonious, mutually oriented relationships that permeate throughout the organization. Top management demand that staff identify with government economic objectives and align the organization’s strategy accordingly so that the products produced are marketable. To achieve this, the organization fosters continual interaction among managers throughout the organization’s hierarchy. The chaebol’s organizational learning model encapsulates a “corollary” (continual communication) and “tools” (cultural influence and relationship management), and manifests in a unique strategy that allows management systems to evolve naturally.

Is there a difference in artistic ability between learning -disabled students and "regular-class" students?

Research and practice regarding LO students usually has focussed upon defining and supplementing deficiencies rather than seeking unique talents and capability patterns for learning and expression. This study examined nine dimensions that may constitute artistic or creative talent and compared LDs with "regular-class" students, pair-wise and as groups, for levels and distributions of the dimensions. For 14 LO and 9 "regular-class" elementary-school subjects, both genders, data were taken by direct observation, from a standardized test and assessments by two practicing artists. Assessments by artists were in concord. LOs improved more in "Composition". No other significant class, age or gender-related differences were found.

The Ethics Of Reconciling : Learning From Canada’s Truth And Reconciliation Commission

In 2008, the Truth and Reconciliation Commission of Canada (TRC) was initiated to address the historical and contemporary injustices and impacts of Indian Residential Schools. Of the many goals of the TRC, I focus on reconciliation and how the TRC aims to promote this through public education and engagement. To explore this, I consider two questions: 1) who does the TRC include in the process of reconciliation? And 2) how might I, as someone who is not Indigenous (specifically, as someone who is “white”), be engaged by the TRC? Ethical queries arise which speak to broader concerns about the TRC’s capability to fulfill its public education goals. I raise several concerns about whether the TRC’s plan to convoke the col- lective will result in over-simplifying the process by relying on blunt, poorly defined identity categories that erase the heterogeneity of those residing in Canada, as well as the complexity of the conflict among us. I attempt to situate myself in-between proclamations of “success” or “failure” of the TRC, to better understand what can be learned from contested truths and experiences of uncertainty.