您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

《山东大学学报(理学版)》 ›› 2018, Vol. 53 ›› Issue (12): 90-98.doi: 10.6040/j.issn.1671-9352.0.2017.627

• • 上一篇    下一篇

求解具有约束的l1-范数问题的神经网络模型

李翠平,高兴宝*   

  1. 陕西师范大学数学与信息科学学院, 陕西 西安 710062
  • 出版日期:2018-12-20 发布日期:2018-12-18
  • 作者简介:李翠平(1982— ), 女, 博士研究生, 讲师, 研究方向为最优化方法(神经网络模型). E-mail:cuipli@126.com*通信作者简介:高兴宝(1966— ), 男, 博士, 教授, 博士生导师, 研究方向为智能优化方法、最优化理论与算法. E-mail:xinbaog@snnu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61273311,61603235)

A neural network for solving l1-norm problems with constraints

LI Cui-ping, GAO Xing-bao*   

  1. School of Mathematics and Information Science, Shaanxi Normal University, Xian 710062, Shaanxi, China
  • Online:2018-12-20 Published:2018-12-18

摘要: 提出了一个解约束最小 l1-范数问题的单层神经网络模型。与已有神经网络模型相比,提出的模型所需神经元数少且层数少。通过引入 Lyapunov 函数,证明了该模型的稳定性和收敛性。数值试验结果表明所提出的模型具有良好的性能。

关键词: l1-范数问题, 神经网络, 单层, 稳定性

Abstract: This paper presents a one-layer neural network model for solving l1-norm problems with constraints. Compared with some existing neural network models, the proposed model needs fewer neurons and has a simpler structure. The stability and convergence of the proposed model are proved by introducing a Lyapunov function. Some simulation examples are used to illustrate its validity and transient behaviors.

Key words: l1-norm problem, neural network, one-layer, stability

中图分类号: 

  • O241.6
[1] KINDERLEHRER D, STAMPACCHIA G. An introduction to variational inequalities and their applications[M]. Salt Lake City: Academic Press, 1980.
[2] ORTEGA J M, RHEINBOLDT W C. Iterative solution of nonlinear equation in several variables[M]. New York: Academic Press, 1970.
[3] SOLODOV M V, TSENG P. Modified projection-type methods for monotone variational inequalities[J]. SIAM Journal on Control and Optimization, 1996, 34(5): 1814-1830.
[4] TSENG P. A modified forward-backward splitting method for maximal monotone mappings[J]. SIAM Journal on Control and Optimization, 2000, 38(2): 431-446.
[5] BERGER J O. Statistical decision theory and Bayesian analysis[M]. New York: Springer, 1985.
[6] HARKER P T, PANG Jongshi. Finite dimensional variational inequality and nonlinear complementarity problem: a survey of theory, algorithms, and applications[J]. Math Program: Series B, 1990, 48:161-220.
[7] HOPFIELD J J, TANK D W. Computing with neural circuits: a model[J]. Science, 1986, 233(4764):625-633.
[8] TANK D W, HOPFIELD J J. Simple neural optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit[J]. IEEE Transactions on Circuits and Systems, 1986, 33(5):533-541.
[9] 夏又生, 叶大振. 解L1-范数极小化问题的神经网络[J]. 电子学报, 1997, 25(11):99-102. XIA Yousheng, YE Dazhen. Neural network for solving L1-norm minimization problem[J]. Acta Electronica Sinica, 1997, 25(11):99-102.
[10] XIA Yousheng, WANG Jun. Neural networks for solving least absolute and related problems[J]. Neurocomputing, 1998, 19:13-21.
[11] WANG Zhishun, CHEUNG J, XIA Yousheng, et al. Minimum fuel neural networks and their applications to overcomplete signal representations[J]. IEEE Transactions on Fundamental Theory and Applications, 2000, 47(8):1146-1159.
[12] WANG Zhishun, HE Zhenya, CHEN Jiande. Robust time delay estimation of bioelectric signals[J]. IEEE Transactions on Bio-medical Engineering, 2005, 52(3):454-462.
[13] WANG Zhishun, PETERSON B S. Constrained least absolute deviation neural networks[J]. IEEE Transactions on Neural Networks, 2008, 19(2):273-283.
[14] XIA Yousheng, KAMEL M. Cooperative recurrent neural networks for the constrained L1 estimator[J]. IEEE Transactions on Signal Processing, 2007, 55(7):3192-3206.
[15] XIA Yousheng, KAMEL M. A generalized least absolute deviation method for parameter estimation of autoregressive signals[J]. IEEE Transactions on Neural Networks, 2008, 19(1):107-118.
[16] LIU Qingshan, WANG Jun. L1-Minimization algorithms for sparse signal reconstruction based on a projection neural network[J]. IEEE Transactions on Neural Networks, 2016, 27(6):89-707.
[17] XIA Yousheng, SUN Changyin, ZHENG Weixing. Discrete-time neural network for fast solving large linear L1 estimation problems and its application to image restoration[J]. IEEE Transactions on Neural Networks, 2012, 23(5):812-820.
[18] LI Cuiping, GAO Xingbao, LI Yawei, et al. A new neural network for l1-norm programing[J]. Neurocomputing, 2016, 202:98-103.
[19] XIA Yousheng. A compact cooperative recurrent neural network for computing general constrained l1 norm estimators[J]. IEEE Transactions on Signal Processing, 2009, 57(9):3693-3697.
[20] GAO Xingbao. A novel neural network for nonlinear convex programming[J]. IEEE Transactions on Neural Networks, 2004, 15(3):613-621.
[21] LIU Qingshan, WANG Jun. A projection neural network for constrained quadratic minimax optimization[J]. IEEE Transactions on Neural Networks, 2015, 26:2891-2900.
[22] XUE Xiaoping, BIAN Wei. A project neural network for solving degenerate quadratic minimax problem with linear constraints[J]. Neurocomputing, 2009, 72:1826-1838.
[23] HU Xiaolin. Applications of the general projection neural network in solving extended linear-quadratic programming problems with linear constraints[J]. Neurocomputing, 2009, 72:1131-1137.
[24] QIN Sitian, LE Xinyi, WANG Jun. A neurodynamic optimization approach to bilevel quadratic programming[J]. IEEE Transactions on Neural Networks, 2017, 28(11):2580-2591.
[25] LE Xinyi, WANG Jun. A two-time-scale neurodynamic approach to constrained minimax optimization[J]. IEEE Transactions on Neural Networks, 2017, 28(3):620-629.
[26] GAO Xingbao, LI Cuiping. A new neural network for convex quadratic minimax problems with box and equality constraints[J]. Computers and Chemical Engineering, 2017, 104:1-10.
[27] GAO Xingbao. A neural network for a class of extended linear variational inequalities[J]. Chinese Journal of Electronics, 2001, 10(4):471-475.
[28] GAO Xingbao, LIAO Lizhi. A neural network for monotone variational inequalities with linear constraints[J]. Physics Letters. A, 2003, 307(2):118-128.
[29] DU Lili, GAO Xingbao. A neural network with finite-time convergence for a class of variational inequalities[C] // International Conference on Intelligent Computing. New York: Springer, 2006, 4113:32-41.
[30] GAO Xingbao, LIAO Lizhi. A new projection-based neural network for constrained variational inequalities[J]. IEEE Transactions on Neural Networks, 2009, 15(4):622-628.
[31] GAO Xingbao, LIAO Lizhi. A novel neural network for generally constrained variational inequalities[J]. Computers and Chemical Engineering, 2017, 104:1-10.
[32] GAO Xingbao, LIAO Lizhi. A novel neural network for a class of convex quadratic minimax problems[J]. Neural Computation, 2006, 18(8):1818-1846.
[33] HU Xiaolin, SUN Changyin, ZHANG Bo. Design of recurrent neural networks for solving constrained least absolute deviation problems[J]. IEEE Transactions on Neural Networks, 2010, 21(7):1073-1086.
[34] RUSZCZYNSHI A. Nonlinear optimization[M]. New Jersey: Princrton University Press, 2006
[35] ZABCZYK J. Mathematical control theory: an introduction[M]. New York: Academic Press, 1992.
[36] GAO Xingbao, LIAO Lizhi. A new one-layer network for linear and quadratic programming[J]. IEEE Transactions on Neural Networks, 2010, 21(6):918-929.
[1] 肖炜茗,王贵君. 基于Bernstein多项式的SISO三层前向神经网络的设计与逼近[J]. 山东大学学报(理学版), 2018, 53(9): 55-61.
[2] 刘华,叶勇,魏玉梅,杨鹏,马明,冶建华,马娅磊. 一类离散宿主-寄生物模型动态研究[J]. 山东大学学报(理学版), 2018, 53(7): 30-38.
[3] 张芳芳,曹兴超. 基于字面和语义相关性匹配的智能篇章排序[J]. 山东大学学报(理学版), 2018, 53(3): 46-53.
[4] 刘明明,张敏情,刘佳,高培贤. 一种基于浅层卷积神经网络的隐写分析方法[J]. 山东大学学报(理学版), 2018, 53(3): 63-70.
[5] 冯孝周,徐敏,王国珲. 具有B-D反应项与毒素影响的捕食系统的共存解[J]. 《山东大学学报(理学版)》, 2018, 53(12): 53-61.
[6] 宋亮,冯金顺,程正兴. 多重Gabor框架的存在性与稳定性[J]. 山东大学学报(理学版), 2017, 52(8): 17-24.
[7] 秦静,林鸿飞,徐博. 基于示例语义的音乐检索模型[J]. 山东大学学报(理学版), 2017, 52(6): 40-48.
[8] 白宝丽,张建刚,杜文举,闫宏明. 一类随机的SIR流行病模型的动力学行为分析[J]. 山东大学学报(理学版), 2017, 52(4): 72-82.
[9] 李金兰,梁春丽. 强Gorenstein C-平坦模[J]. 山东大学学报(理学版), 2017, 52(12): 25-31.
[10] 王长弘,王林山. 基于忆阻器的S-分布时滞随机神经网络的均方指数稳定性[J]. 山东大学学报(理学版), 2016, 51(5): 130-135.
[11] 薛文萍,纪培胜. 混合AQC函数方程在FFNLS上的HUR稳定性[J]. 山东大学学报(理学版), 2016, 51(4): 1-8.
[12] 蔡超. 一类Kolmogorov型方程的系数反演问题[J]. 山东大学学报(理学版), 2016, 51(4): 127-134.
[13] 付娟,张睿,王彩军,张婧. 具有Beddington-DeAngelis功能反应项的捕食-食饵扩散模型的稳定性[J]. 山东大学学报(理学版), 2016, 51(11): 115-122.
[14] 武婧媛,石瑞青. 一类包含媒体报道的SEQIHRS传染病模型的分析[J]. 山东大学学报(理学版), 2016, 51(1): 115-122.
[15] 林青腾,魏凤英. 具有饱和发病率随机SIQS传染病模型的稳定性[J]. 山东大学学报(理学版), 2016, 51(1): 128-134.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 杨军. 金属基纳米材料表征和纳米结构调控[J]. 山东大学学报(理学版), 2013, 48(1): 1 -22 .
[2] 孙小婷1,靳岚2*. DOSY在寡糖混合物分析中的应用[J]. J4, 2013, 48(1): 43 -45 .
[3] 杨伦,徐正刚,王慧*,陈其美,陈伟,胡艳霞,石元,祝洪磊,曾勇庆*. RNA干扰沉默PID1基因在C2C12细胞中表达的研究[J]. J4, 2013, 48(1): 36 -42 .
[4] 杨莹,江龙*,索新丽. 容度空间上保费泛函的Choquet积分表示及相关性质[J]. J4, 2013, 48(1): 78 -82 .
[5] 李永明1, 丁立旺2. PA误差下半参数回归模型估计的r-阶矩相合[J]. J4, 2013, 48(1): 83 -88 .
[6] 杨永伟1,2,贺鹏飞2,李毅君2,3. BL-代数的严格滤子[J]. 山东大学学报(理学版), 2014, 49(03): 63 -67 .
[7] 赵同欣1,刘林德1*,张莉1,潘成臣2,贾兴军1. 紫藤传粉昆虫与花粉多型性研究[J]. 山东大学学报(理学版), 2014, 49(03): 1 -5 .
[8] 汤晓宏1,胡文效2*,魏彦锋2,蒋锡龙2,张晶莹2,. 葡萄酒野生酿酒酵母的筛选及其生物特性的研究[J]. 山东大学学报(理学版), 2014, 49(03): 12 -17 .
[9] 王碧玉,曹小红*. 算子矩阵的Browder定理的摄动[J]. 山东大学学报(理学版), 2014, 49(03): 90 -95 .
[10] 于秀清. P-集合的(σ,τ)-扩展模型与其性质[J]. 山东大学学报(理学版), 2014, 49(04): 90 -94 .