Richard Mitchell

TL;DR: A systematic overview of basic research on model selection approaches for linear-in-the-parameter models, including Bayesian parameter regularisation and models selective criteria based on the cross validation and experimental design is presented.

TL;DR: The authors outline a new training algorithm which reduces both the number of iterations and training time required for convergence of multilayer perceptrons, compared to standard back-propagation and conjugate gradient descent algorithms.

TL;DR: The fundamental principles of micrprocessor systems are described and these are illustrated with reference to two microprocessors, the 32-bit MC68020 from Motorola and a single chip microcomputer, the 8051 from Intel; and in addition, interfacing to the general purpose STE bus is described.

TL;DR: The identification of non-linear systems using only observed finite datasets has become a mature research area over the last two decades as discussed by the authors, and many linear-in-the-parameter models with universal approximation capabilities have been intensively studied and widely used due to the availability of many linear learning algorithms and their inherent convergence conditions.

TL;DR: Stigmergy (loosely, the effect of communication through the environment) in relation to the Internet, especially with regard to Web-based learning is considered, before its use in the construction of CoFIND (Collaborative Filter In N Dimensions).