Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore-Penrose Inverse and Its Circuit Schematic

Bing Zhang; Yuhua Zheng; Shuai Li; Xinglong Chen; Yao Mao; Duc Truong Pham

doi:10.1109/TCSII.2025.3530639

Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore-Penrose Inverse and Its Circuit Schematic

Bing Zhang, Yuhua Zheng, Shuai Li, Xinglong Chen, Yao Mao^*, Duc Truong Pham

^*Corresponding author for this work

BA56 Cognitive production industry

Research output: Contribution to journal › Article › Scientific › peer-review

1 Citation (Scopus)

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.

Original language	English
Pages (from-to)	499-503
Number of pages	5
Journal	IEEE Transactions on Circuits and Systems II: Express Briefs
Volume	72
Issue number	3
DOIs	https://doi.org/10.1109/TCSII.2025.3530639
Publication status	Published - 2025
MoE publication type	A1 Journal article-refereed

Funding

This work was supported by the National Natural Science Foundation of China under Grant 62271109.

Keywords

circuit schematic
manipulator
time-varying matrix Moore-Penrose inverse
Zeroing neural network

Access to Document

10.1109/TCSII.2025.3530639

Cite this

@article{b31b7117f1c741198d55e5467e5c1562,

title = "Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore-Penrose Inverse and Its Circuit Schematic",

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.",

keywords = "circuit schematic, manipulator, time-varying matrix Moore-Penrose inverse, Zeroing neural network",

author = "Bing Zhang and Yuhua Zheng and Shuai Li and Xinglong Chen and Yao Mao and Pham, {Duc Truong}",

year = "2025",

doi = "10.1109/TCSII.2025.3530639",

language = "English",

volume = "72",

pages = "499--503",

journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",

issn = "1549-7747",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

number = "3",

}

TY - JOUR

T1 - Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore-Penrose Inverse and Its Circuit Schematic

AU - Zhang, Bing

AU - Zheng, Yuhua

AU - Li, Shuai

AU - Chen, Xinglong

AU - Mao, Yao

AU - Pham, Duc Truong

PY - 2025

Y1 - 2025

N2 - 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.

AB - 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.

KW - circuit schematic

KW - manipulator

KW - time-varying matrix Moore-Penrose inverse

KW - Zeroing neural network

UR - http://www.scopus.com/inward/record.url?scp=86000372070&partnerID=8YFLogxK

U2 - 10.1109/TCSII.2025.3530639

DO - 10.1109/TCSII.2025.3530639

M3 - Article

AN - SCOPUS:86000372070

SN - 1549-7747

VL - 72

SP - 499

EP - 503

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

IS - 3

ER -

Inverse-Free Hybrid Spatial-Temporal Derivative Neural Network for Time-Varying Matrix Moore-Penrose Inverse and Its Circuit Schematic

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this