A New Computational Approach to the Levenberg-Marquardt Learning Algorithm

被引:0
|
作者
Bilski, Jaroslaw [1 ]
Kowalczyk, Barosz [1 ]
Smolag, Jacek [1 ]
机构
[1] Czestochowa Tech Univ, Inst Computat Intelligence, Czestochowa, Poland
来源
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2022, PT I | 2023年 / 13588卷
关键词
Neural network learning algorithm; Levenberg-marquardt learning algorithm; Vector computations; Approximation; Classification; NEURO-FUZZY SYSTEMS; PARALLEL REALIZATION; NONLINEAR REGRESSIONS; NETWORKS; IDENTIFICATION;
D O I
10.1007/978-3-031-23492-7_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A new parallel computational approach to the Levenberg-Marquardt learning algorithm is presented. The proposed solution is based on the AVX instructions to effectively reduce the high computational load of this algorithm. Detailed parallel neural network computations are explicitly discussed. Additionally obtained acceleration is shown based on a few test problems.
引用
收藏
页码:16 / 26
页数:11
相关论文
共 50 条
  • [21] A Levenberg-Marquardt Algorithm Based Incremental Scheme for Complex-Valued Neural Networks
    Zhang, Shufang
    Huang, He
    Han, Ziyang
    2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 1479 - 1485
  • [22] A new damping strategy of Levenberg-Marquardt algorithm with a fuzzy method for inverse heat transfer problem parameter estimation
    Sajedi, Ramin
    Faraji, Javad
    Kowsary, Farshad
    INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER, 2021, 126
  • [23] A Levenberg-Marquardt Learning Applied for Recurrent Neural Identification and Control of a Wastewater Treatment Bioprocess
    Baruch, Ieroham S.
    Mariaca-Gaspar, Carlos R.
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2009, 24 (11) : 1094 - 1114
  • [24] Solution of the Inverse Spectral Problem for a Rod Weakened by Transverse Cracks by the Levenberg-Marquardt Optimization Algorithm
    Lebedev, I. M.
    Shifrin, E. I.
    MECHANICS OF SOLIDS, 2019, 54 (06) : 857 - 872
  • [25] The data filtering based multiple-stage Levenberg-Marquardt algorithm for Hammerstein nonlinear systems
    Ji, Yan
    Kang, Zhen
    Liu, Ximei
    INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2021, 31 (15) : 7007 - 7025
  • [26] Parameter identification of solar cell model using Levenberg-Marquardt algorithm combined with simulated annealing
    Dkhichi, Fayrouz
    Oukarfi, Benyounes
    Fakkar, Abderrahim
    Belbounaguia, Noureddine
    SOLAR ENERGY, 2014, 110 : 781 - 788
  • [27] Levenberg-Marquardt multi-classification using hinge loss function
    Ozyildirim, Buse Melis
    Kiran, Mariam
    NEURAL NETWORKS, 2021, 143 : 564 - 571
  • [28] Parameter extraction of photovoltaic module model by using Levenberg-Marquardt algorithm based on simulated annealing method
    Dkhichi, Fayrouz
    JOURNAL OF COMPUTATIONAL ELECTRONICS, 2023, 22 (04) : 1128 - 1139
  • [29] Research and application of RBF neural network based on modified Levenberg-Marquardt
    Yang, Yanxia
    Wang, Pu
    Gao, Xuejin
    Gao, Huihui
    Qi, Zeyang
    JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING, 2022, 22 (05) : 1597 - 1619
  • [30] Detection of illegal consumers using pattern classification approach combined with Levenberg-Marquardt method in smart grid
    Ghasemi, Ali Akbar
    Gitizadeh, Mohsen
    INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2018, 99 : 363 - 375