Details of Grant 

EPSRC Reference:	GR/J75425/01
Title:	NOVEL DEVELOPMENTS IN LEARNING THEORY FOR NEURAL NETWORKS
Principal Investigator:	Bishop, Professor C
Other Investigators:	Bounds, Professor D Bounds, Professor D Lowe, Professor D
Researcher Co-Investigators:
Project Partners:
Department:	Computer Science & Applied Mathematics
Organisation:	Aston University
Scheme:	Standard Research (Pre-FEC)
Starts:	01 July 1994	Ends:	30 June 1997	Value (£):	251,757
EPSRC Research Topic Classifications:
EPSRC Industrial Sector Classifications:
Related Grants:
Panel History:
Summary on Grant Application Form
This project will develop new practical techniques for complexity optimisation (determining the architecture of the network and the values of regularisation parameters) based on principled approaches from statistical learning theory, for both static and dynamic feedforward networks. It will draw on disparate, but closely related, techniques from learning theory, information criteria, PAC learnability, and Bayesian inference, and will involve the extension of techniques from Kalman filters, stochastic approximation and kernel density estimation to the neural network domain. The work programme will include systematic comparison with current methods, and demonstrations of the accuracy of predicted generalisation performance. This is an ambitious project which will bring substantial gains in the practical utility of neural network techniques, and yet which has a high probability of success as it builds directly on recent theoretical developments. The work programme involves three stages of formulation of generic techniques, development of practical methods of application to real-world problems, and demonstration and benchmarking across a wide range of example data sets. It is believed that the techniques which will emerge from this project will have a significant impact on the way neural network development for real applications is undertaken.
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.aston.ac.uk