George MacLeod Coghill

Learn More
Qualitative Reasoning offers an approach to analyse system behaviours where standard numerical techniques are impossible or impractical. The theory behind Qualitative Reasoning is very simple, however current implementations are not very efficient. We have developed a Qualitative Reasoning engine with a novel parallel abstract architecture. Recognising(More)
Data-to-text natural language generation techniques do not currently impart deep meaning in their output and leave it to an expert user to draw causal inferences. Frequently, the expert is adding meaning that would be present in data sources that could be made available to the NLG system. As the system is intended to convey as much information as possible,(More)
Checking the function of an external pacemaker can be time consuming both as a routine maintenance task and after the repair of a fault. An instrument is described which is easy to use and contributes to a higher standard of maintenance by considerably reducing the time taken and by eliminating the need for the interconnection of specialized test equipment.
In may real time applications a system needs to be trained quickly on a small amount of new data and then generalise on unseen data. This is a challenging task for neural networks especially when applied to difficult problems such as adaptive speech recognition. An experimental comparison between three recently introduced on-line adaptive connectionist(More)
  • 1