A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons
- Submitting institution
-
University of Northumbria at Newcastle
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 22063351
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2018.2833077
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 123
- Volume
- 30
- Issue
- 1
- ISSN
- 2162-237X
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2018
- 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
-
4
- Research group(s)
-
E - Intelligent Systems Research Group (iSRG)
- Citation count
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This novel supervised learning approach for training spiking-neurons to transform streams of spatio-temporal input spike trains into highly precise output firing patterns has significant implications for neuroprosthetics/neuroengineering. Belatreche was invited to provide a keynote speech on the bio-inspired computational aspects of this article at the IEEE ICTAEE’18 (The third international Conference on Advanced Technologies and Electrical Engineering, Algeria, December 2018, http://conferences.univ-skikda.dz/ictee/index.php). The research was conducted in collaboration with the Computational Intelligence Laboratory, University of Electronic Science and Technology of China, Chengdu.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
