High-Dimensional Function Approximation With Neural Networks for Large Volumes of Data
- Submitting institution
-
University of Keele
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 353
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2017.2651985
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 500
- Volume
- 29
- Issue
- 2
- ISSN
- 2162-2388
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2017
- URL
-
https://ieeexplore.ieee.org/abstract/document/7833076
- 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
-
0
- Research group(s)
-
-
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a novel theoretical underpinning (including formal proofs) of the approximation properties and performance of neural networks applied in combination with dimension reduction methods. This paves the way for provably-valid applications of such techniques in the context of engineering and control problems, for example to deal with high-dimensional sensor data. Further research has expanded the theoretical and experimental investigation (e.g. IJCNN-2018, https://doi.org/fgdn).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -