| EPSRC Reference: |
GR/L78338/01 |
| Title: |
NOVEL LOGIC BASED NEURAL NETWORK ARCHITECTURES FOR MULTIDIMENSIONAL DATA |
| Principal Investigator: |
Howells, Professor G |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Engineering & Digital Arts |
| Organisation: |
University of Kent |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 January 1998 |
Ends: |
31 December 1998 |
Value (£): |
50,829
|
| EPSRC Research Topic Classifications: |
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
The traditional approach to artificial neural network design is to associate real valued weights with the connections between the neurons or processing units contained within the network. The purpose of this proposal is to generalise upon this idea by exploiting the advantages offered by a merger of the ideas contained within the areas of traditional Artificial Neural network design and Constructive type theory. The result of such a proposal would be to produce a neural network architecture capable of manipulating the formal logical expressions associated with Constructive Type Theory and hence efficiently handle application domains associated with complex multi-dimensional data. In order to exploit such a configuration, a network simulator would be produced which would be capable of generalising from a set of known samples of a problem to produce a distributed algorithmic solution to the problem which would be guaranteed to behave correctly within its specification constraints. The proposal aims to build upon a previous simulator architecture produced by the author where Clifford Algebra were employed to represent multi-dimensional data within a neural network architecture.
|
|
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.kent.ac.uk |