Sparse Bayesian Nonlinear System Identification using Variational Inference
- Submitting institution
-
Staffordshire University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 6231
- Type
- D - Journal article
- DOI
-
10.1109/TAC.2018.2813004
- Title of journal
- IEEE Transactions on Automatic Control
- Article number
- -
- First page
- 4172
- Volume
- 63
- Issue
- 12
- ISSN
- 0018-9286
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2018
- URL
-
https://dx.doi.org/10.1109/TAC.2018.2813004
- 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
-
3
- Research group(s)
-
B - Centre for Smart Systems, AI and Cybersecurity (CSSAIC)
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Sparse Bayesian models of systems are important as they allow uncertainty in the model to be quantified and overfitting to be controlled aiding generalisation. The significance of this paper is that it presents a computationally efficient approach to sparse Bayesian nonlinear system identification that can be applied to a wide range of systems. The approach is demonstrated on the modelling of soft actuators which are becoming increasingly important for compliant robots and in prostheses.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -