{"title":"时变矩阵Moore-Penrose逆的无逆混合时空导数神经网络及其电路原理图","authors":"Bing Zhang;Yuhua Zheng;Shuai Li;Xinglong Chen;Yao Mao;Duc Truong Pham","doi":"10.1109/TCSII.2025.3530639","DOIUrl":null,"url":null,"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.","PeriodicalId":13101,"journal":{"name":"IEEE Transactions on Circuits and Systems II: Express Briefs","volume":"72 3","pages":"499-503"},"PeriodicalIF":4.0000,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore–Penrose Inverse and Its Circuit Schematic\",\"authors\":\"Bing Zhang;Yuhua Zheng;Shuai Li;Xinglong Chen;Yao Mao;Duc Truong Pham\",\"doi\":\"10.1109/TCSII.2025.3530639\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":13101,\"journal\":{\"name\":\"IEEE Transactions on Circuits and Systems II: Express Briefs\",\"volume\":\"72 3\",\"pages\":\"499-503\"},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2025-01-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Circuits and Systems II: Express Briefs\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10843719/\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Circuits and Systems II: Express Briefs","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10843719/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore–Penrose Inverse and Its Circuit Schematic
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.
期刊介绍:
TCAS II publishes brief papers in the field specified by the theory, analysis, design, and practical implementations of circuits, and the application of circuit techniques to systems and to signal processing. Included is the whole spectrum from basic scientific theory to industrial applications. The field of interest covered includes:
Circuits: Analog, Digital and Mixed Signal Circuits and Systems
Nonlinear Circuits and Systems, Integrated Sensors, MEMS and Systems on Chip, Nanoscale Circuits and Systems, Optoelectronic
Circuits and Systems, Power Electronics and Systems
Software for Analog-and-Logic Circuits and Systems
Control aspects of Circuits and Systems.