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
  • [31] The neural network approximation method for solving multidimensional nonlinear inverse problems of geophysics
    M. I. Shimelevich
    E. A. Obornev
    I. E. Obornev
    E. A. Rodionov
    Izvestiya, Physics of the Solid Earth, 2017, 53 : 588 - 597
  • [32] Inverse-backlash-compensation neural network nonlinear predictive control and simulation
    Wei, D
    Zhang, ML
    SYSTEM SIMULATION AND SCIENTIFIC COMPUTING, VOLS 1 AND 2, PROCEEDINGS, 2005, : 1165 - 1169
  • [33] Experiments in neural network inverse modelling based control for a class of nonlinear systems
    Petlenkov, E
    Rüstern, E
    BEC 2004: PROCEEDING OF THE 9TH BIENNIAL BALTIC ELECTRONICS CONFERENCE, 2004, : 145 - 148
  • [34] Neural network approach to inverse problems solution: Nonlinear boundary conditions identification
    Ratajewicz-Mikolajczak, E
    Starzynski, J
    Sikora, J
    NON-LINEAR ELECTROMAGNETIC SYSTEMS: ADVANCED TECHNIQUES AND MATHEMATICAL METHODS, 1998, 13 : 397 - 400
  • [35] A neural network for forward and inverse nonlinear Fourier transforms for fibre optic communication
    Zhang, Wen Qi
    Chan, Terence H.
    Afshar, V. Shahraam
    OPTICS AND LASER TECHNOLOGY, 2024, 176
  • [36] The Neural Network Approximation Method for Solving Multidimensional Nonlinear Inverse Problems of Geophysics
    Shimelevich, M. I.
    Obornev, E. A.
    Obornev, I. E.
    Rodionov, E. A.
    IZVESTIYA-PHYSICS OF THE SOLID EARTH, 2017, 53 (04) : 588 - 597
  • [37] Deep Convolutional Neural Network Approach for Solving Nonlinear Inverse Scattering Problems
    Li, Lianlin
    Wang, Long Gang
    Acero, Daniel Ospina
    Teixeira, Fernando L.
    2019 IEEE INTERNATIONAL SYMPOSIUM ON ANTENNAS AND PROPAGATION AND USNC-URSI RADIO SCIENCE MEETING, 2019, : 219 - 220
  • [38] Enabling Secure in-Memory Neural Network Computing by Sparse Fast Gradient Encryption
    Cai, Yi
    Chen, Xiaoming
    Tian, Lu
    Wang, Yu
    Yang, Huazhong
    2019 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD), 2019,
  • [39] Gradient auxiliary physics-informed neural network for nonlinear biharmonic equation
    Liu, Yu
    Ma, Wentao
    ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS, 2023, 157 : 272 - 282
  • [40] PID gradient algorithm for neural network based generalized nonlinear PID controller
    Tan, Yonghong
    Dang, Xuanju
    Achiel, R.
    Van Cauwenberghe, Achiel R.
    Mehrdad Saif
    Kongzhi Lilun Yu Yinyong/Control Theory and Applications, 2000, 17 (06): : 861 - 867
12345