| EPSRC Reference: |
GR/K55219/01 |
| Title: |
PERFORMANCE ASSESSMENT AND GENERALIZABILITY OF NEURAL NETWORKS |
| Principal Investigator: |
Hand, Professor D |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Mathematics & Statistics |
| Organisation: |
The Open University |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 October 1995 |
Ends: |
30 September 1997 |
Value (£): |
80,907
|
| EPSRC Research Topic Classifications: |
|
| EPSRC Industrial Sector Classifications: |
| Aerospace, Defence and Marine |
Financial Services |
| Retail |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
- To explore the theory and properties of performance criteria, other than misclassification rate, for supervised learning of feed-forward neural networks. Different applications have different requirements and it is important to match the criterion to the application.- To develop the theory of generalisability and sample complexity. Generalisation ability is the most important property of a neural network in practice. However, it currently has little applicable theoretical basis.- To use the criteria from the former in extending the latter.- To apply the theory to a wide range of practical problems with commercial and industrial significance.
|
|
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: |
|