An Improved Recurrent Network for Online Equality-Constrained Quadratic Programming

	An Improved Recurrent Network for Online Equality-Constrained Quadratic Programming
	Ke Chen; Zhaoxiang Zhang
	2016-11-28
会议日期	28-30 November 2016
会议地点	Beijing, China
关键词	Recurrent Networks Online Equality-constrained Quadratic Programming Global Exponential Convergence Robustness Analysis
英文摘要	Encouraged by the success of conventional GradientNet and recently-proposed ZhangNet for online equality-constrained quadratic programming problem, an improved recurrent network and its electronic implementation are firstly proposed and developed in this paper. Exploited in the primal form of quadratic programming with linear equality constraints, the proposed neural model can solve the problem effectively. Moreover, compared to the existing recurrent networks, i.e., GradientNet (GN) and ZhangNet (ZN), our model can theoretically guarantee superior global exponential convergence performance. 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 for online equality-constrained quadratic programming.
会议录	BICS 2016
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/13247]
专题	自动化研究所_类脑智能研究中心
通讯作者	Zhaoxiang Zhang
推荐引用方式 GB/T 7714	Ke Chen,Zhaoxiang Zhang. An Improved Recurrent Network for Online Equality-Constrained Quadratic Programming[C]. 见:. Beijing, China. 28-30 November 2016.