| EPSRC Reference: |
GR/R74574/01 |
| Title: |
Silicon Spiking Systems: Collective Parallel Computation and Adaptive Sensory Systems |
| Principal Investigator: |
Smith, Professor LS |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computing Science and Mathematics |
| Organisation: |
University of Stirling |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 May 2002 |
Ends: |
31 August 2005 |
Value (£): |
268,208
|
| EPSRC Research Topic Classifications: |
| Digital Signal Processing |
New & Emerging Comp. Paradigms |
| System on Chip |
VLSI Design |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
| Panel Date | Panel Name | Outcome |
|
08 Nov 2001
|
Electronics, Comms & Functional Materials
|
Deferred
|
|
|
Summary on Grant Application Form |
|
As System-on-Chip transistor density increases, new applications will emerge and new architectures must be explored for VLSI chips with more than 10^7 transistors. As feature size decreases to 500 Angstroms (towards the end of this decade), mismatch and noise problems impact in a manner and at a level far beyond that in current technology. For the most part, the design community has not begun to address this problem. While some ameliorating technological steps are emerging, most of the imperfections in such tiny devices can not be made to disappear and radically new paradigms are required to perform useful computation with small, inaccurate, noisy and (if low-power) slow devices. Neural systems have evolved that compute accurately and rapidly in the presence of similar problems. For example, neuronal sensor systems retrieve perceptually relevant information accurately and rapidly, through slow and noisy processing units and despite the intrinsic noise in the system. We propose solutions which are similar to those taken by neural systems: collective computation techniques, based on spiking neurons, techniques which make use of internal adaptivity (mediated by floating gates) to provide resilient parallel computing. We will implement CMOS chips to support and explore these techniques, applying them to tasks in real-time sensing, including auditory scene analysis and distance analysis in vision.
|
|
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.stir.ac.uk |