Two Birds, One Stone: Combining Student Assessment and Socio-Legal Research

We describe here a method of assessment for students. A number of short-comings of traditional assessment methods, especially essays and examinations, are discussed and an alternative assessment method, the student project, is suggested. The method aims not just to overcome the short-comings of more traditional methods, but also to provide over-worked and under-resourced academics with viable primary data for socio-legal research work. Limitations to the method are discussed, with proposals for minimising the impact of these limitations. The whole �student project� approach is also discussed with reference to the Quality Assurance Agency benchmark standards for law degrees, standards which are expected of all institutions in the UK.

Integrated structure selection and parameter optimisation for eng-genes neural models

The eng-genes concept involves the use of fundamental known system functions as activation functions in a neural model to create a 'grey-box' neural network. One of the main issues in eng-genes modelling is to produce a parsimonious model given a model construction criterion. The challenges are that (1) the eng-genes model in most cases is a heterogenous network consisting of more than one type of nonlinear basis functions, and each basis function may have different set of parameters to be optimised; (2) the number of hidden nodes has to be chosen based on a model selection criterion. This is a mixed integer hard problem and this paper investigates the use of a forward selection algorithm to optimise both the network structure and the parameters of the system-derived activation functions. Results are included from case studies performed on a simulated continuously stirred tank reactor process, and using actual data from a pH neutralisation plant. The resulting eng-genes networks demonstrate superior simulation performance and transparency over a range of network sizes when compared to conventional neural models. (c) 2007 Elsevier B.V. All rights reserved.