A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96989273
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2018.2797801
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 5394
- Volume
- 29
- Issue
- 11
- ISSN
- 2162-237X
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2018
- URL
-
http://dx.doi.org/10.1109/TNNLS.2018.2797801
- 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
-
3
- Research group(s)
-
C - Cybersecurity, privacy and human centred computing
- Citation count
- 18
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We propose a new learning algorithm for multilayer spiking neural networks by incorporating the latest biological research findings. Wang et al. (https://doi.org/10.3389/fnins.2019.00252) described our algorithm as “The first kind of supervised delay learning algorithms”. The distinct features of our algorithm inspired the development of effective learning methods for deep spiking networks. For example, Al-Jamali & Al-Raweshidy (https://doi.org/10.1109/JSYST.2020.2996185) developed a new algorithm for spike ISDN-IoT networks by modifying a training algorithm based on the spike backpropagation of our algorithm.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -