Details of Grant 

EPSRC Reference:	GR/L03088/02
Title:	COMBINING SPATIALLY-DISTRIBUTED PREDICTIONS FROM NEURAL NETWORKS
Principal Investigator:	Williams, Professor C
Other Investigators:	Nabney, Professor IT
Researcher Co-Investigators:
Project Partners:	BAE Systems QinetiQ
Department:	Sch of Informatics
Organisation:	University of Edinburgh
Scheme:	Standard Research (Pre-FEC)
Starts:	01 April 1998	Ends:	23 March 1999	Value (£):	59,825
EPSRC Research Topic Classifications:
EPSRC Industrial Sector Classifications:	Aerospace, Defence and Marine
Related Grants:
Panel History:
Summary on Grant Application Form
Neural networks have been used very successfully in a wide variety of domains for performing classification or regression tasks. A characteristic of most currently successful applications is that the input patterns are either independent (as in statistic pattern classification) or related over time, rather than being spatially distributed. To extend the use of neural networks to spatially distributed tasks, such as the prediction of a wind vector-field from remote-sensing data, typically it is necessary to combine local bottom-up predictions with global prior knowledge. This combination can be achieved by using Bayes' theorem to obtain the posterior distribution for the features of interest (the wind-field). The aims of our research are: to develop a principled approach to the fusion of local predictions from neural networks with global spatial prior knowledge: to investigate the relationship between the complexity of the prior and feature detection stages and overall performance: to apply the framework to problems in remote sensing, object recognition and image segmentation: to disseminate the results of the work to collaborators and the relevant industrial and academic communities. The likely benefits include increased accuracy of predictions in remote sensing and image segmentation and reduced time for object recognition.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.ed.ac.uk