| EPSRC Reference: |
GR/R92844/01 |
| Title: |
Establishing the Performance Envelope of Dynet: a new type of history dependent neural network model with potential for process modelling |
| Principal Investigator: |
withers, Professor P |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Materials |
| Organisation: |
University of Manchester, The |
| Scheme: |
ROPA |
| Starts: |
21 April 2003 |
Ends: |
20 April 2005 |
Value (£): |
76,761
|
| EPSRC Research Topic Classifications: |
| Intelligent & Expert Systems |
Materials Processing |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
As part of a project modelling microstructure development during four stand rolling with Alcan, neural network approaches are being assessed. While such models show promise, our work on very complex datasets has identified the need for a more strategic, examination of their capabilities. To this end a new type of neural network model - Dynet has been proposed, but it is yet undeveloped. This is a 2-year feasibility study using idealised data sets to understand better its performance, capabilities, strengths and weaknesses as well as to optimise their architechture before they can be considered for real problems.
|
|
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.man.ac.uk |