On the importance of sluggish state memory for learning long term dependency
- Submitting institution
-
Nottingham Trent University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 25 - 696203
- Type
- D - Journal article
- DOI
-
10.1016/j.knosys.2015.12.024
- Title of journal
- Knowledge-Based Systems
- Article number
- -
- First page
- 104
- Volume
- 96
- Issue
- -
- ISSN
- 0950-7051
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- 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)
-
A - Computing and Informatics Research Centre
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The significance of this output is that it led to a start-up Perceptronix Ltd (Tepper,2018) providing MRN-based solutions to the financial industry on a full-time basis. This output led to follow-up research evaluating MRN against SoA LSTMs: see IEEE SSCI 10.1109/SSCI44817.2019.9002841, IJCNN 10.1109/IJCNN48605.2020.9206823; and collaborations with Binner(Birmingham) and Kelly(Wisconsin Riverside) to apply MRNs to dynamic stochastic general equilibrium models used by Central banks, see ‘Robust sluggish state‐based neural networks for data driven alternatives to DSGEs’ Soc. Economic Measurement: 4th Conf. 2017, ‘Financial Services Indices, Liquidity and Economic Activity’ Bank of England Workshop 2017.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
