Multilayered Echo State Machine: A Novel Architecture and Algorithm
- Submitting institution
-
Edinburgh Napier University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1792556
- Type
- D - Journal article
- DOI
-
10.1109/TCYB.2016.2533545
- Title of journal
- IEEE Transactions on Cybernetics
- Article number
- -
- First page
- 946
- Volume
- 47
- Issue
- 4
- ISSN
- 2168-2267
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2016
- 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
- 31
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This influential paper proposed an innovative approach to model multi-scale features, demonstrating, for the first time, that the addition of multiple-layers of reservoirs through our defined criteria, can provide a robust alternative to conventional reservoir-computing networks. Representative of a body of work from EP/M026981/1, our model showed a significantly improved trade-off between computational complexity and predictive performance in several benchmark datasets and real-world applications. Our multi-layered approach has been exploited in a range of deep learning contexts, and stimulated development of the learning architecture of our Mengshi cognitive vehicle, which won the 2018 World Intelligent Driving Challenge (with Tsinghua University).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -