Gradient Neural Network with Nonlinear Activation for Computing Inner Inverses and the Drazin Inverse

被引：0
|
作者：
Predrag S. Stanimirović
Marko D. Petković
Dimitrios Gerontitis
机构：
[1] University of Niš,Faculty of Sciences and Mathematics
[2] Aristoteleion Panepistimion,undefined
来源：
Neural Processing Letters | 2018年 / 48卷
关键词：
Recurrent neural network; Moore–Penrose inverse; Drazin inverse; Dynamic equation; Activation function; 68T05; 15A09; 65F20;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Two gradient-based recurrent neural networks (GNNs) for solving two matrix equations are presented and investigated. These GNNs can be used for generating various inner inverses, including the Moore–Penrose, and in the computation of the Drazin inverse. Convergence properties of defined GNNs are considered. Certain conditions which impose convergence towards the pseudoinverse, and the Drazin inverse are exactly specified. The influence of nonlinear activation functions on the convergence performance of defined GNN models is investigated. Computer simulation experience further confirms the theoretical results.
引用
收藏
页码：109 / 133
页数：24
相关论文
共 50 条
  • [21] IMPLEMENTING NONLINEAR ACTIVATION FUNCTIONS IN NEURAL NETWORK EMULATORS
    SAMMUT, KM
    JONES, SR
    ELECTRONICS LETTERS, 1991, 27 (12) : 1037 - 1038
  • [22] Neural network based nonlinear inverse dynamics for flight controller design
    Somakumar, R
    Chandrasekhar, J
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON CONTROL APPLICATIONS, VOLS 1 AND 2, 1996, : 187 - 191
  • [23] Artificial Neural Network Based Inverse Model Control Of A Nonlinear Process
    Rajesh, R. J.
    Preethi, R.
    Mehata, Parth
    Pandian, Jaganatha B.
    2015 INTERNATIONAL CONFERENCE ON COMPUTER, COMMUNICATION AND CONTROL (IC4), 2015,
  • [24] Inverse model, identification of nonlinear dynamic system using neural network
    Mang, Ming-Guang
    PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2007, : 2451 - 2455
  • [25] Neural Network-Based Inverse Design of Nonlinear Phononic Crystals
    Huang, Kunqi
    Li, Yuanyuan
    Lai, Yun
    Liu, Xiaozhou
    IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control, 2023, 3 : 166 - 175
  • [26] Nonlinear adaptive inverse control via the unified model neural network
    Jeng, JT
    Lee, TT
    APPLICATIONS AND SCIENCE OF COMPUTATIONAL INTELLIGENCE II, 1999, 3722 : 153 - 162
  • [27] Artificial Neural Network Based Inverse Model Control Of A Nonlinear Process
    Rajesh, R. J.
    Preethi, R.
    Mehata, Parth
    Pandian, Jaganatha B.
    2015 International Conference on Computing, Communication and Security (ICCCS), 2015,
  • [28] Accelerated Gradient Approach For Neural Network Adaptive Control Of Nonlinear Systems
    Le, Duc M.
    Patil, Omkar Sudhir
    Nino, Cristian F.
    Dixon, Warren E.
    2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 3475 - 3480
  • [29] All-optical neural network with nonlinear activation functions
    Zuo, Ying
    Li, Bohan
    Zhao, Yujun
    Jiang, Yue
    Chen, You-Chiuan
    Chen, Peng
    Jo, Gyu-Boong
    Liu, Junwei
    Du, Shengwang
    OPTICA, 2019, 6 (09): : 1132 - 1137
  • [30] Two finite-time convergent Zhang neural network models for time-varying complex matrix Drazin inverse
    Qiao, Sanzheng
    Wang, Xue-Zhong
    Wei, Yimin
    LINEAR ALGEBRA AND ITS APPLICATIONS, 2018, 542 : 101 - 117
12345