Data annotations are an important kind of meta-data that occur in the form of externally assigned descriptions of particular features in Web accessible documents. Such metadata are eventually used in data retrieval tasks on heterogeneous, possible distributed Web-accessible documents. In this paper, we present the model and realization of an annotation… (More)
A novel unsupervised learning method for extracting spatio-temporal invariances has been developed in (Stone, 1995). The learning method works by trying to jointly minimise the short term variance of a unit's output, whilst maximising the long term variance of the output. The learning method has been applied to extracting disparity from a temporal sequence… (More)
A recent study has shown that, when people talk, their changing facial expressions and head movements provide dynamic cues for recognition.
The grey level profiles of adjacent image regions tend to be different, whilst the 'hidden' physical parameters associated with these regions (e.g. surface depth, edge orientation) tend to have similar values. We demonstrate that a network in which adjacent units receive inputs from adjacent image regions learns to code for hidden parameters. The learning… (More)
ii DEDICATION For my grandfather iii ACKNOWLEDGEMENTS Above all I would like to thank Kevin Gurney for his generous and astute supervision. Many thanks are also due to Jackie Andrade, for supervision and advice, especially in the early stages; to the Basal Ganglia research group, for support of all kinds (especially Mark Humphries and Ric Wood); Neil Porter… (More)
Background: The need for terminology systems in healthcare has long been established (1). However, to be useful in computer environments, controlled terminologies must be made accessible to computer applications. A common approach is to use a network accessible "terminology server". In this paper, we describe an open source terminology server written in the… (More)