Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root
Abstract Zeroing neural networks (ZNN) have shown their state-of-the-art performance on dynamic problems. However, ZNNs are vulnerable to perturbations, which causes reliability concerns in these models owing to the potentially severe consequences. Although it has been reported that some models poss...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-12-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-022-00954-9 |
| _version_ | 1797769243913093120 |
|---|---|
| author | Chengze Jiang Chaomin Wu Xiuchun Xiao Cong Lin |
| author_facet | Chengze Jiang Chaomin Wu Xiuchun Xiao Cong Lin |
| author_sort | Chengze Jiang |
| collection | DOAJ |
| description | Abstract Zeroing neural networks (ZNN) have shown their state-of-the-art performance on dynamic problems. However, ZNNs are vulnerable to perturbations, which causes reliability concerns in these models owing to the potentially severe consequences. Although it has been reported that some models possess enhanced robustness but cost worse convergence speed. In order to address these problems, a robust neural dynamic with an adaptive coefficient (RNDAC) model is proposed, aided by the novel adaptive activation function and robust evolution formula to boost convergence speed and preserve robustness accuracy. In order to validate and analyze the performance of the RNDAC model, it is applied to solve the dynamic matrix square root (DMSR) problem. Related experiment results show that the RNDAC model reliably solves the DMSR question perturbed by various noises. Using the RNDAC model, we are able to reduce the residual error from 10 $$^1$$ 1 to 10 $$^{-4}$$ - 4 with noise perturbed and reached a satisfying and competitive convergence speed, which converges within 3 s. |
| first_indexed | 2024-03-12T21:06:09Z |
| format | Article |
| id | doaj.art-8c7fa876f76643ab8e259084ad193fed |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-03-12T21:06:09Z |
| publishDate | 2022-12-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-8c7fa876f76643ab8e259084ad193fed2023-07-30T11:27:52ZengSpringerComplex & Intelligent Systems2199-45362198-60532022-12-01944213422610.1007/s40747-022-00954-9Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square rootChengze Jiang0Chaomin Wu1Xiuchun Xiao2Cong Lin3School of Electronic and Information Engineering, Guangdong Ocean UniversitySchool of Electronic and Information Engineering, Guangdong Ocean UniversitySchool of Electronic and Information Engineering, Guangdong Ocean UniversitySchool of Electronic and Information Engineering, Guangdong Ocean UniversityAbstract Zeroing neural networks (ZNN) have shown their state-of-the-art performance on dynamic problems. However, ZNNs are vulnerable to perturbations, which causes reliability concerns in these models owing to the potentially severe consequences. Although it has been reported that some models possess enhanced robustness but cost worse convergence speed. In order to address these problems, a robust neural dynamic with an adaptive coefficient (RNDAC) model is proposed, aided by the novel adaptive activation function and robust evolution formula to boost convergence speed and preserve robustness accuracy. In order to validate and analyze the performance of the RNDAC model, it is applied to solve the dynamic matrix square root (DMSR) problem. Related experiment results show that the RNDAC model reliably solves the DMSR question perturbed by various noises. Using the RNDAC model, we are able to reduce the residual error from 10 $$^1$$ 1 to 10 $$^{-4}$$ - 4 with noise perturbed and reached a satisfying and competitive convergence speed, which converges within 3 s.https://doi.org/10.1007/s40747-022-00954-9Dynamic matrix square rootTime-dependentZeroing neural networkAdaption coefficient |
| spellingShingle | Chengze Jiang Chaomin Wu Xiuchun Xiao Cong Lin Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root Complex & Intelligent Systems Dynamic matrix square root Time-dependent Zeroing neural network Adaption coefficient |
| title | Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root |
| title_full | Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root |
| title_fullStr | Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root |
| title_full_unstemmed | Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root |
| title_short | Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root |
| title_sort | robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root |
| topic | Dynamic matrix square root Time-dependent Zeroing neural network Adaption coefficient |
| url | https://doi.org/10.1007/s40747-022-00954-9 |
| work_keys_str_mv | AT chengzejiang robustneuraldynamicswithadaptivecoefficientappliedtosolvethedynamicmatrixsquareroot AT chaominwu robustneuraldynamicswithadaptivecoefficientappliedtosolvethedynamicmatrixsquareroot AT xiuchunxiao robustneuraldynamicswithadaptivecoefficientappliedtosolvethedynamicmatrixsquareroot AT conglin robustneuraldynamicswithadaptivecoefficientappliedtosolvethedynamicmatrixsquareroot |