Event-driven continuous STDP learning with deep structure for visual pattern recognition
- Submitting institution
-
University of Lincoln
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 31010
- Type
- D - Journal article
- DOI
-
10.1109/tcyb.2018.2801476
- Title of journal
- IEEE Transactions on Cybernetics
- Article number
- -
- First page
- 1377
- Volume
- 49
- Issue
- 4
- ISSN
- 2168-2267
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2018
- URL
-
http://doi.org/10.1109/tcyb.2018.2801476
- 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
-
1
- Research group(s)
-
-
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- To achieve reliable and fast visual pattern recognition with limited time and learning samples like human is always challenging. This paper created a visual system similar to ventral stream in human with fast learning capability - a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -