Details of Grant 

EPSRC Reference:	GR/K09007/01
Title:	CERTIFICATION OF NEURAL NETWORKS
Principal Investigator:	Morgan, Dr G
Other Investigators:	Austin, Professor J
Researcher Co-Investigators:
Project Partners:
Department:	Computer Science
Organisation:	University of York
Scheme:	Standard Research (Pre-FEC)
Starts:	06 March 1995	Ends:	05 July 1996	Value (£):	52,175
EPSRC Research Topic Classifications:
EPSRC Industrial Sector Classifications:
Related Grants:
Panel History:
Summary on Grant Application Form
The research proposed here will investigate certification issues for neural networks which are to be used in safety critical applications. There are two central themes: to evaluate the applicability of existing well established certification techniques to neural network-based systems, and to develop and propose new techniques where those existing are inadequate. The certification of neural networks is shortly to become a crucial issue. Safety critical systems based upon neural networks are currently under development by several industries (aircraft manufacturers, pharmaceutical companies, etc.). However, methodologies to guarantee that these systems behave as expected are poorly developed.We will develop these methodologies by using those current techniques which are relevant and developing new techniques to deal with issues peculiar to neural networks.
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.york.ac.uk