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
  • [31] Cost Sensitive Improved Levenberg Marquardt Algorithm for Imbalanced Data
    Shinde, S. B.
    Sayyad, S. S.
    2016 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH, 2016, : 318 - 321
  • [32] MODIFIED LEVENBERG-MARQUARDT METHOD FOR ROSSLER CHAOTIC SYSTEM FUZZY MODELING TRAINING
    Wang, Yu-Hui
    Wu, Qing-Xian
    Jiang, Chang-Sheng
    Xue, Ya-Li
    Fang, Wei
    INTERNATIONAL JOURNAL OF MODERN PHYSICS B, 2009, 23 (24): : 4953 - 4961
  • [33] Long-term prediction of chaotic time series with multi-step prediction horizons by a neural network with Levenberg-Marquardt learning algorithm
    Mirzaee, Hossein
    CHAOS SOLITONS & FRACTALS, 2009, 41 (04) : 1975 - 1979
  • [34] QUADRATIC CONVERGENCE OF LEVENBERG-MARQUARDT METHOD FOR ELLIPTIC AND PARABOLIC INVERSE ROBIN PROBLEMS
    Jiang, Daijun
    Feng, Hui
    Zou, Jun
    ESAIM-MATHEMATICAL MODELLING AND NUMERICAL ANALYSIS-MODELISATION MATHEMATIQUE ET ANALYSE NUMERIQUE, 2018, 52 (03): : 1085 - 1107
  • [35] Nonmonotone Levenberg-Marquardt training of recurrent neural architectures for processing symbolic sequences
    Peng, Chun-Cheng
    Magoulas, George D.
    NEURAL COMPUTING & APPLICATIONS, 2011, 20 (06) : 897 - 908
  • [36] Fuzzy Approximation by a Novel Levenberg-Marquardt Method for Two-Degree-of-Freedom Hypersonic Flutter Model
    Wang, Y. H.
    Zhu, L.
    Wu, Q. X.
    Jiang, C. S.
    JOURNAL OF VIBRATION AND ACOUSTICS-TRANSACTIONS OF THE ASME, 2014, 136 (04):
  • [37] Levenberg-Marquardt iterative regularization for the pulse-type impact-force reconstruction
    Gunawan, Fergyanto E.
    JOURNAL OF SOUND AND VIBRATION, 2012, 331 (25) : 5424 - 5434
  • [38] Automatic Hemiplegia Type Detection (Right or Left) Using the Levenberg-Marquardt Backpropagation Method
    Christou, Vasileios
    Arjmand, Alexandros
    Dimopoulos, Dimitrios
    Varvarousis, Dimitrios
    Tsoulos, Ioannis
    Tzallas, Alexandros T.
    Gogos, Christos
    Tsipouras, Markos G.
    Glavas, Evripidis
    Ploumis, Avraam
    Giannakeas, Nikolaos
    INFORMATION, 2022, 13 (02)
  • [39] ADAPTIVE DETERMINATION OF THE DAMPING COEFFICIENT OF THE LEVENBERG-MARQUARDT ALGORITHM USING TYPE-2 FUZZY IN INVERSE HEAT TRANSFER PROBLEMS
    Sajedi, Ramin
    Faraji, Javad
    Samadi, Forooza
    Kowsary, Farshad
    PROCEEDINGS OF ASME 2024 HEAT TRANSFER SUMMER CONFERENCE, HT 2024, 2024,
  • [40] An online optimization method for extracting parameters of multi-parameter PV module model based on adaptive Levenberg-Marquardt algorithm
    Wang, Mengyuan
    Xu, Xiaoyuan
    Yan, Zheng
    Wang, Han
    ENERGY CONVERSION AND MANAGEMENT, 2021, 245
12345