Abstract:
This brief introduces the Inverse-free hybrid spatial-temporal derivative neural network (IHSTDNN), a novel neural network that integrates principles from gradient neural...Show MoreMetadata
Abstract:
This brief introduces the Inverse-free hybrid spatial-temporal derivative neural network (IHSTDNN), a novel neural network that integrates principles from gradient neural networks (GNN) and zeroing neural networks (ZNN) to address the time-varying matrix Moore-Penrose inverse. The IHSTDNN features an explicit dynamic structure, eliminating the need for inverse operations. The design of its circuit is outlined, and the model’s convergence and robustness are examined theoretically. Numerical simulations and experimental data demonstrate that the IHSTDNN outperforms other existing models, achieving a faster convergence rate and reduced steady-state error.
Published in: IEEE Transactions on Circuits and Systems II: Express Briefs ( Volume: 72, Issue: 3, March 2025)
Funding Agency:
National Key Laboratory of Optical Field Manipulation Science and Technology, the Key Laboratory of Optical Engineering, and the Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
University of Chinese Academy of Sciences, Beijing, China
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China
Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland
VTT-Technical Research Centre of Finland, Oulu, Finland
National Key Laboratory of Optical Field Manipulation Science and Technology, the Key Laboratory of Optical Engineering, and the Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
University of Chinese Academy of Sciences, Beijing, China
National Key Laboratory of Optical Field Manipulation Science and Technology, the Key Laboratory of Optical Engineering, and the Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
University of Chinese Academy of Sciences, Beijing, China
Department of Mechanical Engineering, University of Birmingham, Birmingham, U.K.
Contents National Key Laboratory of Optical Field Manipulation Science and Technology, the Key Laboratory of Optical Engineering, and the Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
University of Chinese Academy of Sciences, Beijing, China
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China
Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland
VTT-Technical Research Centre of Finland, Oulu, Finland
National Key Laboratory of Optical Field Manipulation Science and Technology, the Key Laboratory of Optical Engineering, and the Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
University of Chinese Academy of Sciences, Beijing, China
National Key Laboratory of Optical Field Manipulation Science and Technology, the Key Laboratory of Optical Engineering, and the Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
University of Chinese Academy of Sciences, Beijing, China
Department of Mechanical Engineering, University of Birmingham, Birmingham, U.K.
