A Primal Neural Network for Online Equality-Constrained Quadratic Programming

被引：0
作者：
Ke Chen
Zhaoxiang Zhang
机构：
[1] Tampere University of Technology,Lab of Signal Processing
[2] CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT),National Laboratory of Pattern Recognition
[3] Institute of Automation,undefined
[4] Chinese Academy of Sciences (NLPR,undefined
[5] CASIA),undefined
[6] University of Chinese Academy of Sciences (UCAS),undefined
来源：
Cognitive Computation | 2018年 / 10卷
关键词：
Recurrent neural networks; Online equality-constrained quadratic programming; Global exponential convergence; Robustness analysis;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This paper aims at solving online equality-constrained quadratic programming problem, which is widely encountered in science and engineering, e.g., computer vision and pattern recognition, digital signal processing, and robotics. Recurrent neural networks such as conventional GradientNet and ZhangNet are considered as powerful solvers for such a problem in light of its high computational efficiency and capability of circuit realisation. In this paper, an improved primal recurrent neural network and its electronic implementation are proposed and analysed. Compared to the existing recurrent networks, i.e. GradientNet and ZhangNet, our network can theoretically guarantee superior global exponential convergence. Robustness performance of our such neural model is also analysed under a large model implementation error, with the upper bound of stead-state solution error estimated. Simulation results demonstrate theoretical analysis on the proposed model, which also verify the effectiveness of the proposed model for online equality-constrained quadratic programming.
引用
收藏
页码：381 / 388
页数：7
相关论文
共 50 条
[11]   Design and Analysis of a Self-Adaptive Zeroing Neural Network for Solving Time-Varying Quadratic Programming [J].
Dai, Jianhua ;
Yang, Xing ;
Xiao, Lin ;
Jia, Lei ;
Liu, Xinwang ;
Wang, Yaonan .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (10) :7135-7144
[12]   An Inexact Sequential Quadratic Programming Method for Learning and Control of Recurrent Neural Networks [J].
Adeoye, Adeyemi D. ;
Bemporad, Alberto .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 36 (02) :2762-2776
[13]   Quasi-Lagrangian Neural Network for Convex Quadratic Optimization [J].
Costantini, Giovanni ;
Perfetti, Renzo ;
Todisco, Massimiliano .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (10) :1804-1809
[14]   Time-Varying Quadratic-Programming-Based Error Redefinition Neural Network Control and Its Application to Mobile Redundant Manipulators [J].
Zheng, Lunan ;
Zhang, Zhijun .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2022, 67 (11) :6151-6158
[15]   Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming [J].
Fazlyab, Mahyar ;
Morari, Manfred ;
Pappas, George J. .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2022, 67 (01) :1-15
[16]   A recurrent neural network for real-time semidefinite programming [J].
Jiang, DC ;
Wang, J .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (01) :81-93
[17]   A One-Layer Recurrent Neural Network for Constrained Nonsmooth Optimization [J].
Liu, Qingshan ;
Wang, Jun .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2011, 41 (05) :1323-1333
[18]   A New Varying-Parameter Convergent-Differential Neural-Network for Solving Time-Varying Convex QP Problem Constrained by Linear-Equality [J].
Zhang, Zhijun ;
Lu, Yeyun ;
Zheng, Lunan ;
Li, Shuai ;
Yu, Zhuliang ;
Li, Yuanqing .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2018, 63 (12) :4110-4125
[19]   A complete proof of global exponential convergence of a neural network for quadratic optimization with bound constraints [J].
Liang, XB .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (03) :636-639
[20]   Online-Growing Neural Network Control for Dissolved Oxygen Concentration [J].
Qiao, Junfei ;
Su, Yin ;
Yang, Cuili .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (05) :6794-6803
12345