Abstract
Given the critical role of zeroing neural networks (ZNN) in various fields and the practical demand for models in effectively resisting real-time noise, this study introduces a novel anti-noise integral zeroing neural network (AN-IZNN) model alongside its enhanced counterpart (EAN-IZNN), for the applications of matrix problem solving. Theoretical analysis demonstrates their ability to achieve convergence even under different noise conditions. Both theoretical analyses and simulation validations highlight the superior performance of the proposed models over existing neural network models. Notably, the root mean square error of the proposed AN-IZNN and EAN-IZNN models is reduced by 92.6249% and 91.4178%, respectively, compared to scenarios without the proposed method, demonstrating the effectiveness of the solution.
| Original language | English |
|---|---|
| Pages (from-to) | 1083-1099 |
| Number of pages | 17 |
| Journal | Mathematics and Computers in Simulation |
| Volume | 240 |
| DOIs | |
| Publication status | Published - Feb 2026 |
| MoE publication type | A1 Journal article-refereed |
Funding
This work was supported by the Key Program of the National Natural Science Foundation of China (No. 52232002) on Multiscale Structure Design and In-Situ Phase Reconstruction under Dynamic High-Temperature Conditions for Synergistic Enhancement of Unburned Refractories, the Shanghai Technical Service Center for Advanced Ceramics Structure Design and Precision Manufacturing (No. 20DZ2294000), and the Local University Capacity Building Program of the Science and Technology Commission of Shanghai Municipality (No. 23010500400).
Keywords
- Activation function
- Integral neural network
- Neural network application
- Noise robustness
- Time-varying problem
- Zeroing neural network