EPSRC logo

Details of Grant 

EPSRC Reference: GR/K55288/01
Title: AUTONOMOUS TRAINING ALGORITHMS FOR NEURAL NETWORKS
Principal Investigator: Rockett, Dr P
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Infoterra Ltd
Department: Electronic and Electrical Engineering
Organisation: University of Sheffield
Scheme: Standard Research (Pre-FEC)
Starts: 01 November 1995 Ends: 31 August 1998 Value (£): 73,592
EPSRC Research Topic Classifications:
EPSRC Industrial Sector Classifications:
Related Grants:
Panel History:  
Summary on Grant Application Form
The aim of this project is to deliver two autonomous neural network training algorithms which will provide statistically founded solutions to the problem of static pattern clarification. This will include finalising a theoretical evaluation of the Bhattacharryya similarity metric for the automatic selection of computational models of data, and the development of two complementary neural network architectures. One architecture which aims to grow a neural architecture to solve a problem and the second which aims to reduce the internal complexity of the network in order to maximise generalisation ability. This project will be evaluated in the industrial domain on the labelling of satellite imagery and provide a practical use of these algorithms for immediate industrial exploitation.
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.shef.ac.uk