A neuromorphic network for generic multivariate data classification
- Submitting institution
-
University of Hertfordshire
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13600704
- Type
- D - Journal article
- DOI
-
10.1073/pnas.1303053111
- Title of journal
- Proceedings of the National Academy of Sciences of the United States of America
- Article number
- -
- First page
- 2081
- Volume
- 111
- Issue
- 6
- ISSN
- 0027-8424
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2014
- 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
-
2
- Research group(s)
-
-
- Citation count
- 47
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The first proof-of-concept for pattern recognition on neuromorphic hardware - other published accounts at that time did either not run on neuromorphic hardware, or were incapable of generic pattern recognition. Has led to Dr Schmuker becoming a member of and funded by H2020 flagship HBP in 2014 until the present day. The conversion of multivariate data to a semidefinite positive representation through "virtual receptors" solves the general problem of how to represent multivariate data with spikes and has been taken up in various variants by works on neuromorphic hardware citing this paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -