EPSRC logo

Details of Grant 

EPSRC Reference: GR/M12889/01
Title: FAULT-TOLERANT AND BAYESIAN APPROACHES TO SELF- ORGANISING NEURAL NETWORKS
Principal Investigator: Allinson, Professor NM
Other Investigators:
Yin, Professor H
Researcher Co-Investigators:
Project Partners:
Rolls-Royce Plc (UK)
Department: Electrical Engineering & Electronics
Organisation: UMIST
Scheme: Standard Research (Pre-FEC)
Starts: 01 January 1999 Ends: 31 December 2001 Value (£): 176,191
EPSRC Research Topic Classifications:
Artificial Intelligence
EPSRC Industrial Sector Classifications:
No relevance to Underpinning Sectors
Related Grants:
Panel History:  
Summary on Grant Application Form
Self-organising neural networks, in particular Kohonen's SOM and its variants, have been widely studied and employed in many diverse applications. There are several important application areas (e.g. plant monitoring, data-mining) where they have demonstrated their worth.An incomplete theoretical foundation for some important parameters, especially when compared with other mainstream supervised neural systems, has frustrated both academic, industrial and commercial communities. Providing such a foundation will not only improve the existing application domain but permit a well-founded extension to other domains.The project will address these fundamental issues, in association with practical experimentation, and provide both a unified theoretical framework and a variety of extended algorithms and treatments for pattern recognition, data visualisation and data compression. Strong links with collaborators, and existing application activities, will ensure these crucial developments, are consistently related to practical constraints and needs. The outcomes of this work will take the form of conventional published papers, extensive technical reports and user guidelines, and software (for use in MatLab, Windows and Unix environments - with integration with the SOM-PAK software suite).
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: