A Primal Neural Network for Online Equality-Constrained Quadratic Programming

doi:10.1007/s12559-017-9510-4

	A Primal Neural Network for Online Equality-Constrained Quadratic Programming
	Chen, Ke 1; Zhang, Zhaoxiang2,3,4
刊名	COGNITIVE COMPUTATION
	2018-04-01
卷号	10 期号:2 页码:381-388
关键词	Recurrent Neural Networks Online Equality-constrained Quadratic Programming Global Exponential Convergence Robustness Analysis
DOI	10.1007/s12559-017-9510-4
文献子类	Article
英文摘要	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.
WOS关键词	SUPPORT VECTOR MACHINE ; MATRIX-INVERSION ; ROBUSTNESS ANALYSIS ; REGRESSION ; EQUATIONS ; DYNAMICS ; MINIMIZATION ; COMPUTATION ; ARM
WOS研究方向	Computer Science ; Neurosciences & Neurology
语种	英语
WOS记录号	WOS:000430190600017
资助机构	National Natural Science Foundation of China(61773375 ; Microsoft Collaborative Research Project ; Academy of Finland(298700) ; 61375036 ; 61511130079)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/20441]
专题	自动化研究所_类脑智能研究中心
作者单位	1.Tampere Univ Technol, Signal Proc Lab, Tampere, Finland 2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, CASIA, NLPR, Beijing, Peoples R China 4.UCAS, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Chen, Ke,Zhang, Zhaoxiang. A Primal Neural Network for Online Equality-Constrained Quadratic Programming[J]. COGNITIVE COMPUTATION,2018,10(2):381-388.
APA	Chen, Ke,&Zhang, Zhaoxiang.(2018).A Primal Neural Network for Online Equality-Constrained Quadratic Programming.COGNITIVE COMPUTATION,10(2),381-388.
MLA	Chen, Ke,et al."A Primal Neural Network for Online Equality-Constrained Quadratic Programming".COGNITIVE COMPUTATION 10.2(2018):381-388.