| EPSRC Reference: |
GR/R54569/01 |
| Title: |
Toward Spiking Neural Computations with Applications |
| Principal Investigator: |
Feng, Professor J |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Engineering and Informatics |
| Organisation: |
University of Sussex |
| Scheme: |
Fast Stream |
| Starts: |
01 January 2002 |
Ends: |
31 December 2004 |
Value (£): |
62,481
|
| EPSRC Research Topic Classifications: |
| New & Emerging Comp. Paradigms |
|
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
The aim of this project is to develop novel learning rules and apply them to solving practical problems. The learning rule is derived under the principle of maximisation of the mutual information of input-output, which has been proposed and widely used in research into artificial neuronal networks. In computational neuroscience, on the other hand, recent developments in modelling single neurones mean that we know exactly the input-output relationship of some neurone models such as the integrate-and-fire model and the IF-FHN model etc. Combining these two approaches together, we are able to develop principle learning rules which rely directly on known (realistic) input-output relationships of a spiking neurone. After theoretically understanding the proposed learning rules, comparing with biological data, we are then going to apply the rule to some visual tasks. A direct application is blind separation: to separate a linear mixture of input signals. Further applications include imagine segmentation, motion segmentation etc.
|
|
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.sussex.ac.uk |