Norm‐based zeroing neural dynamics for time‐variant non‐linear equations
Abstract Zeroing neural dynamic (ZND) model is widely deployed for time‐variant non‐linear equations (TVNE). Various element‐wise non‐linear activation functions and integration operations are investigated to enhance the convergence performance and robustness in most proposed ZND models for solving...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543345903501312 |
|---|---|
| author | Linyan Dai Hanyi Xu Yinyan Zhang Bolin Liao |
| author_facet | Linyan Dai Hanyi Xu Yinyan Zhang Bolin Liao |
| author_sort | Linyan Dai |
| collection | DOAJ |
| description | Abstract Zeroing neural dynamic (ZND) model is widely deployed for time‐variant non‐linear equations (TVNE). Various element‐wise non‐linear activation functions and integration operations are investigated to enhance the convergence performance and robustness in most proposed ZND models for solving TVNE, leading to a huge cost of hardware implementation and model complexity. To overcome these problems, the authors develop a new norm‐based ZND (NBZND) model with strong robustness for solving TVNE, not applying element‐wise non‐linear activated functions but introducing a two‐norm operation to achieve finite‐time convergence. Moreover, the authors develop a discrete‐time NBZND model for the potential deployment of the model on digital computers. Rigorous theoretical analysis for the NBZND is provided. Simulation results substantiate the advantages of the NBZND model for solving TVNE. |
| format | Article |
| id | doaj-art-e64de4ae82fe4766b22d9bb7473a0dcd |
| institution | Kabale University |
| issn | 2468-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj-art-e64de4ae82fe4766b22d9bb7473a0dcd2025-01-13T14:05:51ZengWileyCAAI Transactions on Intelligence Technology2468-23222024-12-01961561157110.1049/cit2.12360Norm‐based zeroing neural dynamics for time‐variant non‐linear equationsLinyan Dai0Hanyi Xu1Yinyan Zhang2Bolin Liao3College of Cyber Security Jinan University Guangzhou ChinaCollege of Cyber Security Jinan University Guangzhou ChinaCollege of Cyber Security Jinan University Guangzhou ChinaCollege of Information Science and Engineering Jishou University Jishou ChinaAbstract Zeroing neural dynamic (ZND) model is widely deployed for time‐variant non‐linear equations (TVNE). Various element‐wise non‐linear activation functions and integration operations are investigated to enhance the convergence performance and robustness in most proposed ZND models for solving TVNE, leading to a huge cost of hardware implementation and model complexity. To overcome these problems, the authors develop a new norm‐based ZND (NBZND) model with strong robustness for solving TVNE, not applying element‐wise non‐linear activated functions but introducing a two‐norm operation to achieve finite‐time convergence. Moreover, the authors develop a discrete‐time NBZND model for the potential deployment of the model on digital computers. Rigorous theoretical analysis for the NBZND is provided. Simulation results substantiate the advantages of the NBZND model for solving TVNE.https://doi.org/10.1049/cit2.12360finite‐time convergencenorm‐based zeroing neural dynamicsrobustnesstime‐variant nonlinear equationzeroing neural dynamic |
| spellingShingle | Linyan Dai Hanyi Xu Yinyan Zhang Bolin Liao Norm‐based zeroing neural dynamics for time‐variant non‐linear equations CAAI Transactions on Intelligence Technology finite‐time convergence norm‐based zeroing neural dynamics robustness time‐variant nonlinear equation zeroing neural dynamic |
| title | Norm‐based zeroing neural dynamics for time‐variant non‐linear equations |
| title_full | Norm‐based zeroing neural dynamics for time‐variant non‐linear equations |
| title_fullStr | Norm‐based zeroing neural dynamics for time‐variant non‐linear equations |
| title_full_unstemmed | Norm‐based zeroing neural dynamics for time‐variant non‐linear equations |
| title_short | Norm‐based zeroing neural dynamics for time‐variant non‐linear equations |
| title_sort | norm based zeroing neural dynamics for time variant non linear equations |
| topic | finite‐time convergence norm‐based zeroing neural dynamics robustness time‐variant nonlinear equation zeroing neural dynamic |
| url | https://doi.org/10.1049/cit2.12360 |
| work_keys_str_mv | AT linyandai normbasedzeroingneuraldynamicsfortimevariantnonlinearequations AT hanyixu normbasedzeroingneuraldynamicsfortimevariantnonlinearequations AT yinyanzhang normbasedzeroingneuraldynamicsfortimevariantnonlinearequations AT bolinliao normbasedzeroingneuraldynamicsfortimevariantnonlinearequations |