A discrete-time recurrent neural network for solving quadratic programs with application to FIR filter synthesis

被引:0
|
作者
Tang, WS [1 ]
机构
[1] Chinese Univ Hong Kong, Dept Automat & Comp Aided Engn, Hong Kong, Hong Kong, Peoples R China
来源
SMC 2000 CONFERENCE PROCEEDINGS: 2000 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOL 1-5 | 2000年
关键词
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
A discrete-time recurrent neural network is presented for solving convex quadratic programs. It is the discrete-time version of its continuous-time counterpart which is developed in [11]. Sharing the same characteristic with its continuous-time counterpart, the proposed discrete-time neural network could compute the exact optimal solution to a quadratic program without using any penalty parameter. However, the discrete-time version is more desirable in practical realization in view of the availability of digital hardware and the good compatibility to computer. The condition for the neural network globally converging to the optimal solution of a quadratic program is given. The neural network is applied to FIR filter synthesis for illustrating its effectiveness.
引用
收藏
页码:2491 / 2496
页数:6
相关论文
共 50 条
  • [41] Symmetry discrete-time delayed neural network
    Xingjian Wang
    Chunrui Zhang
    Advances in Difference Equations, 2012
  • [42] Discrete-time high order neural network identifier trained with cubature Kalman filter
    Hernandez-Gonzalez, M.
    Hernandez-Vargas, E. A.
    Basin, M., V
    NEUROCOMPUTING, 2018, 322 : 13 - 21
  • [43] Arbitrary FIR filter synthesis using a neural network
    Tan, Y
    He, ZY
    NEURAL PROCESSING LETTERS, 1998, 8 (01) : 9 - 13
  • [44] Region stability analysis for switched discrete-time recurrent neural network with multiple equilibria
    Bao, Gang
    Zeng, Zhigang
    NEUROCOMPUTING, 2017, 249 : 182 - 190
  • [45] Convergence and periodicity of solutions for a class of discrete-time recurrent neural network with two neurons
    Qu, Hong
    Yi, Zhang
    ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 291 - 296
  • [46] Arbitrary FIR Filter Synthesis Using a Neural Network
    Ying Tan
    Zhenya He
    Neural Processing Letters, 1998, 8 : 9 - 13
  • [47] A NOVEL RECURRENT NEURAL NETWORK FOR SOLVING MLCPs AND ITS APPLICATION TO LINEAR AND QUADRATIC PROGRAMMING PROBLEMS
    Effati, Sohrab
    Ghomashi, Abbas
    Abbasi, Masumeh
    ASIA-PACIFIC JOURNAL OF OPERATIONAL RESEARCH, 2011, 28 (04) : 523 - 541
  • [48] Discrete-time neural network with two classes of bias noises for solving time-variant matrix inversion and application to robot tracking
    Peng Miao
    Deyu Wu
    Yanjun Shen
    Zhiqiang Zhang
    Neural Computing and Applications, 2019, 31 : 4879 - 4890
  • [49] Discrete-time neural network with two classes of bias noises for solving time-variant matrix inversion and application to robot tracking
    Miao, Peng
    Wu, Deyu
    Shen, Yanjun
    Zhang, Zhiqiang
    NEURAL COMPUTING & APPLICATIONS, 2019, 31 (09): : 4879 - 4890
  • [50] Discrete-time delayed standard neural. network model and its application
    Liu Meiqin
    SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES, 2006, 49 (02): : 137 - 154