Design and Comprehensive Analysis of a Noise-Tolerant ZNN Model With Limited-Time Convergence for Time-Dependent Nonlinear Minimization
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1448
- Type
- D - Journal article
- DOI
-
10.1109/tnnls.2020.2966294
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 5339
- Volume
- 31
- Issue
- 12
- ISSN
- 1045-9227
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2020
- 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
-
5
- Research group(s)
-
D - Robotics and Embedded Systems (RES)
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in IEEE-TNNLS, arguably the most prestigious journal dealing with theory, design and applications of neural networks and related learning systems, this paper introduces for the first time a novel Zeroing-neural-network (ZNN) that simultaneously achieves limited-time convergence and inherent noise suppression to solve time-dependent nonlinear minimization under various external disturbances. Significantly extending previous work on ZNNs, this research provides theoretical foundations and paves the way toward powerful tools for wide-arranging applicability in robotic control, image processing and multi-agent systems applications. It led to invited talks at universities and labs in China, Canada and Australia and follow-on collaborative supervised PhD projects.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -