Tampere University of Technology

TUTCRIS Research Portal

A Primal Neural Network for Online Equality-Constrained Quadratic Programming

Research output: Contribution to journalArticleScientificpeer-review

Standard

A Primal Neural Network for Online Equality-Constrained Quadratic Programming. / Chen, Ke; Zhang, Zhaoxiang.

In: Cognitive Computation, Vol. 10, No. 2, 2018, p. 381–388.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Chen, K & Zhang, Z 2018, 'A Primal Neural Network for Online Equality-Constrained Quadratic Programming', Cognitive Computation, vol. 10, no. 2, pp. 381–388. https://doi.org/10.1007/s12559-017-9510-4

APA

Vancouver

Author

Chen, Ke ; Zhang, Zhaoxiang. / A Primal Neural Network for Online Equality-Constrained Quadratic Programming. In: Cognitive Computation. 2018 ; Vol. 10, No. 2. pp. 381–388.

Bibtex - Download

@article{21adf90437614bfb94b712803e60fa94,
title = "A Primal Neural Network for Online Equality-Constrained Quadratic Programming",
abstract = "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.",
keywords = "Global exponential convergence, Online equality-constrained quadratic programming, Recurrent neural networks, Robustness analysis",
author = "Ke Chen and Zhaoxiang Zhang",
year = "2018",
doi = "10.1007/s12559-017-9510-4",
language = "English",
volume = "10",
pages = "381–388",
journal = "Cognitive Computation",
issn = "1866-9956",
publisher = "Springer Verlag",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A Primal Neural Network for Online Equality-Constrained Quadratic Programming

AU - Chen, Ke

AU - Zhang, Zhaoxiang

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

KW - Global exponential convergence

KW - Online equality-constrained quadratic programming

KW - Recurrent neural networks

KW - Robustness analysis

U2 - 10.1007/s12559-017-9510-4

DO - 10.1007/s12559-017-9510-4

M3 - Article

VL - 10

SP - 381

EP - 388

JO - Cognitive Computation

JF - Cognitive Computation

SN - 1866-9956

IS - 2

ER -