Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications
Zeroing neural networks (ZNN), as a specialized class of bio-Iinspired neural networks, emulate the adaptive mechanisms of biological systems, allowing for continuous adjustments in response to external variations. Compared to traditional numerical methods and common neural networks (such as gradien...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/5/279 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327558542229504 |
|---|---|
| author | Yufei Wang Cheng Hua Ameer Hamza Khan |
| author_facet | Yufei Wang Cheng Hua Ameer Hamza Khan |
| author_sort | Yufei Wang |
| collection | DOAJ |
| description | Zeroing neural networks (ZNN), as a specialized class of bio-Iinspired neural networks, emulate the adaptive mechanisms of biological systems, allowing for continuous adjustments in response to external variations. Compared to traditional numerical methods and common neural networks (such as gradient-based and recurrent neural networks), this adaptive capability enables the ZNN to rapidly and accurately solve time-varying problems. By leveraging dynamic zeroing error functions, the ZNN exhibits distinct advantages in addressing complex time-varying challenges, including matrix inversion, nonlinear equation solving, and quadratic optimization. This paper provides a comprehensive review of the evolution of ZNN model formulations, with a particular focus on single-integral and double-integral structures. Additionally, we systematically examine existing nonlinear activation functions, which play a crucial role in determining the convergence speed and noise robustness of ZNN models. Finally, we explore the diverse applications of ZNN models across various domains, including robot path planning, motion control, multi-agent coordination, and chaotic system regulation. |
| format | Article |
| id | doaj-art-98a44f6e1aea4618b2e856d13ddb554c |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-98a44f6e1aea4618b2e856d13ddb554c2025-08-20T03:47:49ZengMDPI AGBiomimetics2313-76732025-04-0110527910.3390/biomimetics10050279Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and ApplicationsYufei Wang0Cheng Hua1Ameer Hamza Khan2College of Computer Science and Engineering, Jishou University, Jishou 416000, ChinaCollege of Computer Science and Engineering, Jishou University, Jishou 416000, ChinaSmart City Research Institute (SCRI), Hong Kong Polytechnic University, Kowloon, Hong KongZeroing neural networks (ZNN), as a specialized class of bio-Iinspired neural networks, emulate the adaptive mechanisms of biological systems, allowing for continuous adjustments in response to external variations. Compared to traditional numerical methods and common neural networks (such as gradient-based and recurrent neural networks), this adaptive capability enables the ZNN to rapidly and accurately solve time-varying problems. By leveraging dynamic zeroing error functions, the ZNN exhibits distinct advantages in addressing complex time-varying challenges, including matrix inversion, nonlinear equation solving, and quadratic optimization. This paper provides a comprehensive review of the evolution of ZNN model formulations, with a particular focus on single-integral and double-integral structures. Additionally, we systematically examine existing nonlinear activation functions, which play a crucial role in determining the convergence speed and noise robustness of ZNN models. Finally, we explore the diverse applications of ZNN models across various domains, including robot path planning, motion control, multi-agent coordination, and chaotic system regulation.https://www.mdpi.com/2313-7673/10/5/279zeroing neural network (ZNN)noise-toleranttime-varying problemsconvergenceapplications |
| spellingShingle | Yufei Wang Cheng Hua Ameer Hamza Khan Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications Biomimetics zeroing neural network (ZNN) noise-tolerant time-varying problems convergence applications |
| title | Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications |
| title_full | Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications |
| title_fullStr | Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications |
| title_full_unstemmed | Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications |
| title_short | Advances in Zeroing Neural Networks: Bio-Inspired Structures, Performance Enhancements, and Applications |
| title_sort | advances in zeroing neural networks bio inspired structures performance enhancements and applications |
| topic | zeroing neural network (ZNN) noise-tolerant time-varying problems convergence applications |
| url | https://www.mdpi.com/2313-7673/10/5/279 |
| work_keys_str_mv | AT yufeiwang advancesinzeroingneuralnetworksbioinspiredstructuresperformanceenhancementsandapplications AT chenghua advancesinzeroingneuralnetworksbioinspiredstructuresperformanceenhancementsandapplications AT ameerhamzakhan advancesinzeroingneuralnetworksbioinspiredstructuresperformanceenhancementsandapplications |