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
  • [41] Visualization of Layers Within a Convolutional Neural Network Using Gradient Activation Maps
    McAllister, Dianna
    Mendez, Mauro
    Bermudez, Ariana
    Tyrrell, Pascal N.
    UNIVERSITY OF TORONTO JOURNAL OF UNDERGRADUATE LIFE SCIENCES, 2020, 14 (01)
  • [42] Toward Fuzzy Activation Function Activated Zeroing Neural Network for Currents Computing
    Jin, Jie
    Chen, Weijie
    Ouyang, Aijia
    Liu, Haiyan
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2023, 70 (11) : 4201 - 4205
  • [43] High speed and reconfigurable optronic neural network with digital nonlinear activation
    Wu, Qiuhao
    Fei, Yuhang
    Liu, Jia
    Wang, Liping
    Chen, Qian
    Gu, Guohua
    Sui, Xiubao
    OPTIK, 2021, 247
  • [44] Logish: A new nonlinear nonmonotonic activation function for convolutional neural network
    Zhu, Hegui
    Zeng, Huimin
    Liu, Jinhai
    Zhang, Xiangde
    NEUROCOMPUTING, 2021, 458 : 490 - 499
  • [45] Zeroing neural network approaches for computing time-varying minimal rank outer inverse
    Stanimirovic, Predrag S.
    Mourtas, Spyridon D.
    Mosic, Dijana
    Katsikis, Vasilios N.
    Cao, Xinwei
    Li, Shuai
    APPLIED MATHEMATICS AND COMPUTATION, 2024, 465
  • [46] Neural network α-th order inverse system method for the control of nonlinear continuous systems
    Dai, X
    Liu, J
    Feng, C
    He, D
    IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS, 1998, 145 (06): : 519 - 522
  • [47] Nonlinear dynamic compensation of sensors using inverse-model-based neural network
    Yu, Dongchuan
    Liu, Fang
    Lai, Pik-Yin
    Wu, Aiguo
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2008, 57 (10) : 2364 - 2376
  • [48] Identification of nonlinear system model and inverse model based on conditional invertible neural network
    Chen, Tian
    Zhang, Xingwu
    Wang, Chenxi
    Feng, Xuedan
    Lv, Jiaqiao
    Deng, Jiangtao
    You, Shangqin
    Chen, Xuefeng
    ENGINEERING RESEARCH EXPRESS, 2024, 6 (03):
  • [49] Neural network α-th order inverse system method for the control of nonlinear continuous systems
    Southeast Univ, Nanjing, China
    IEE Proc Control Theory Appl, 6 (519-522):
  • [50] Application of artificial neural network to inverse problems of estimating inner etch of elastoplastic pipe under pressure
    Guan, BT
    Shen, CW
    Xiao, JS
    Cai, YS
    ACTA MECHANICA SOLIDA SINICA, 1996, 9 (01) : 88 - 93
12345