Homeostatic Fault Tolerance in Spiking Neural Networks : A Dynamic Hardware Perspective
- Submitting institution
-
University of York
- Unit of assessment
- 12 - Engineering
- Output identifier
- 55026112
- Type
- D - Journal article
- DOI
-
10.1109/TCSI.2017.2726763
- Title of journal
- Ieee transactions on circuits and systems i-Regular papers
- Article number
- 7995041
- First page
- 687
- Volume
- 65
- Issue
- 2
- ISSN
- 1549-8328
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
8
- Research group(s)
-
B - Intelligent Systems and Nano-Science
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper pioneers application of novel self-tuning spiking neural networks implemented on FPGAs, in noisy environments,funded by the EPSRC SPANNER project (EP/N007050/1, £683,915). The work reported in this paper formed the foundations for a Dstl funded project on ‘Self-repairing neural controllers for autonomous chemical identification’ to deliver a proof of principle demonstrator of fault-tolerant hardware within an autonomous robotic system, capable of mapping hazards chemical environments and identifying key hazards of interest (CDE101169; Contact: Academic Liaison Officer, Dstl).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -