二次最小化问题的有限时间递归神经网络求解

doi:10.13438/j.cnki.jdzk.2019.02.006

吉首大学学报（自然科学版）

二次最小化问题的有限时间递归神经网络求解

张永胜，肖林

（吉首大学信息科学与工程学院，湖南吉首 416000）

出版日期:2019-03-25 发布日期:2019-04-30
通讯作者: 肖林（1986—），男，湖南邵阳人，吉首大学信息科学与工程学院副教授，博士，主要从事递归神经网络和机器人研究.
作者简介:张永胜（1995—），男，湖南永州人，吉首大学信息科学与工程学院硕士研究生，主要从事递归神经网络研究
基金资助:
国家自然科学基金资助项目（61866013，61503152,61563017,61561022,61363073,61363033）;吉首大学校级科研项目(JDY13)

Finite-Time Recursive Neural Network for Quadratic Minimization Problems

ZHANG Yongsheng,XIAO Lin

(School of Information Science and Engineering,Jishou University,Jishou 416000,Hunan China)

Online:2019-03-25 Published:2019-04-30

摘要/Abstract

摘要：

利用一类递归神经网络模型来求解二次最小化问题，在该模型的基础上加入双符号幂激励函数，以加快递归神经网络的收敛速度，甚至达到有限时间收敛.通过调节设计参数λ的取值，递归神经网络的收敛性能可进一步提高.利用MATLAB软件对有限递归神经网络模型进行仿真，数值仿真结果验证了模型求解二次最小化问题的有效性和优越性.

关键词： 二次最小化问题, 有限时间, 递归神经网络模型

Abstract:

A recursive neural network model is utilized for solving the quadratic minimization problem,and a sign-bi-power activation function is added to the network model,which speeds up the convergence of the recursive neural network even to reach the finite-time convergence.Moreover,by adjusting the value of the designing parameter λ,the convergence performance of the recursive neural network can be further improved.Finally,the MATLAB is used to simulate and verify the recursive neural network model,and the numerical simulation results verify the effectiveness and superiority of the proposed finite-time recursive neural network model for solving the quadratic minimization problem.

Key words: quadratic minimization problem, finite-time convergence, recurrent neural network

张永胜，肖林. 二次最小化问题的有限时间递归神经网络求解[J]. 吉首大学学报（自然科学版）, DOI: 10.13438/j.cnki.jdzk.2019.02.006.

ZHANG Yongsheng,XIAO Lin. Finite-Time Recursive Neural Network for Quadratic Minimization Problems[J]. Journal of Jishou University（Natural Sciences Edition), DOI: 10.13438/j.cnki.jdzk.2019.02.006.

参考文献

[1] 叶仲泉,张邦礼,曹长修.Minimax神经网络收敛性分析[J].信息与控制,1997,26(1):1-6.
[2] 赵超越,张友华.小麦赤霉病神经网络和偏最小二乘预测模型[J].吉首大学学报(自然科学版),2017,38(4):47-52.
[3] XIAO Lin,ZHANG Yongsheng,LIAO Bolin,et al.A Velocity-Level Bi-Criteria Optimization Scheme for Coordinated Path Tracking of Dual Robot Manipulators Using Recurrent Neural Network[J].Frontiers in Neurorobotics,2017,11:47-53.
[4] 郑雪莲.非线性最优化问题的若干算法研究[D].青岛：山东科技大学,2005:3-5.
[5] 陈丽,王景芹.可靠性约束函数未知的网路费用最小化快速求解[J].吉首大学学报(自然科学版),2016,37(4):19-24;28.
[6] 钱育蓉,于炯,英昌甜,等.一种分区BP人工神经网络图像差值算法[J].吉首大学学报(自然科学版),2016,37(3):28-33.
[7] 韦建波,张栋柱,罗浩杰,等.基于改进的RBF神经网络的配电网故障诊断模型[J].吉首大学学报(自然科学版),2018,39(1):54-58.
[8] 向秋红,廖柏林,马川.新型递归神经网络求解时变矩阵Moore-Penrose逆[J].吉首大学学报(自然科学版),2017,38(3):31-35.
[9] 汪思成,肖林,严慧玲.基于不同误差函数的神经网络求解线性方程组[J].吉首大学学报(自然科学版),2016,37(6):26-28.
[10] 宋玉阶.求解二次规划问题的神经网络方法[J].武汉大学学报(理学版),2001,47(3):347-350.
[11] 赵华敏,陈开周.解非线性方程组的神经网络方法[J].电子学报,2002,30(4):601-604.
[12] XIAO Lin,ZHANG Yunong.Zhang Neural Network Versus Gradient Neural Network for Solving Time-Varying Linear Inequalities[J].IEEE Transactions on Neural Networks,2011,22(10):1 676-1 684.
[13] ZHANG Yang,CHEN K.Global Exponential Convergence and Stability of Wang Neural Network for Solving Online Linear Equations[J].Electronics Letters,2008,44(2):145-146.
[14] XIAO Lin,DING Sitong,MAO Mingzhi,et al.Finite-Time Convergence Analysis and Verification of Improved ZNN for Real-Time Matrix Inversion[C]∥IEEE International Conference on Information Science & Technology.IEEE,2014:286-289.
[15] LI Shuai,LI Yangming,WANG Zheng.A Class of Finite-Time Dual Neural Networks for Solving Quadratic Programming Pand Its k-Winners-Take-All Application[J].Neural Networks,2013,39:27-39.
[16] XIAO Lin.A New Design Formula Exploited for Accelerating Zhang Neural Network and Its Application to Time-Varying Matrix Inversion[J].Theoretical Computer Science,2016,647:50-58.
[17] XIAO Lin,LIAO Bolin,JIN Jie,et al.A Finite-Time Convergent Dynamic System for Solving Online Simultaneous Linear Equations[J].International Journal of Computer Mathematics,2017,94(9):1 778-1 786.
[18] XIAO Lin.A Finite-Time Convergent Zhang Neural Networkand Its Application to Real-Time Matrix Square Root Finding[J].Neural Computing and Applications,2017:1-8.DOI:10.1007/s00521-017-3010-z.
[19] ZHANG Yunong,JIANG Danchi,WANG Jun.A Recurrent Neural Network for Solving Sylvester Equation with Time-Varying Coefficients[J].IEEE Transactions on Neural Network,2002,13(5):1 053-1 063.

二次最小化问题的有限时间递归神经网络求解

Finite-Time Recursive Neural Network for Quadratic Minimization Problems

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价