Gaussian processes and SVM: Mean field results and leave-one-out

In this chapter, we elaborate on the well-known relationship between Gaussian processes (GP) and Support Vector Machines (SVM). Secondly, we present approximate solutions for two computational problems arising in GP and SVM. The first one is the calculation of the posterior mean for GP classifiers using a `naive' mean field approach. The second one is a leave-one-out estimator for the generalization error of SVM based on a linear response method. Simulation results on a benchmark dataset show similar performances for the GP mean field algorithm and the SVM algorithm. The approximate leave-one-out estimator is found to be in very good agreement with the exact leave-one-out error.

Directing under disqualification:leave to act

Reviews the procedures by which a disqualified director can continue to act. Views this siutation through two recent cases. Highlights that courts should not fetter the Company Directors Disqualification Act 1986, s 17 discretion and reject the approach of earlier cases that in order for leave to be granted, a need on the part of the director or company was a prerequisite.

The future of engineering - Do primary school engineering education interventions leave a lasting impression?

This positional paper proposes a conceptual framework and methodological approach for use in a PhD study investigating the longer term educational and social impact of 'active' engineering focused interventions for children age 8-10 in the UK. The study will critically analyse how a child's participation in an engineering education activity contributes to the Engineering Capital that the child possesses; focusing on how the child's awareness and perceptions about engineering are affected. To achieve this aim it is proposed that Grounded Theory methodology be used to enable an in-depth analysis of participation from the perspective of the child participant. The study proposed will be longitudinal, taking place over three formative years for the education and career aspirations of the child, from age 8-10 to 11-13. Although the research is in its infancy, this paper will provide the opportunity to develop theory in an underdeveloped area of engineering education research.