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] Distributed model calibration using Levenberg-Marquardt algorithm
    Lu, Mark
    Zhu, Liang
    Ling, Li
    Zhangb, Gary
    Chan, Walter
    Zhou, Xin
    OPTICAL MICROLITHOGRAPHY XX, PTS 1-3, 2007, 6520
  • [32] Levenberg-Marquardt Iterative Algorithm for Hammerstein Nonlinear Systems
    Zhou, Lincheng
    Li, Xiangli
    Xu, Huigang
    Zhu, Peiyi
    FOURTH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND INFORMATION SCIENCES (CCAIS 2015), 2015, : 280 - 284
  • [33] Levenberg-Marquardt Algorithm for Orthogonal Fitting of Transition Curves
    Song Z.
    Wang J.
    Li J.
    Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2020, 55 (01): : 144 - 149
  • [34] Radar Target Detection by Using Levenberg-Marquardt Algorithm
    Nasret, Ali Najdet
    Kamal, Ayoub Esam
    Mahmood, Zuhiar Shakor
    PRZEGLAD ELEKTROTECHNICZNY, 2023, 99 (03): : 265 - 270
  • [35] Improvement of the neighborhood based Levenberg-Marquardt algorithm by local adaptation of the learning coefficient
    Toledo, A
    Pinzolas, M
    Ibarrola, JJ
    Lera, G
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (04): : 988 - 992
  • [36] An Improved Levenberg-Marquardt Learning Algorithm for Neural Networks Based on Terminal Attractors
    Batbayar, Batsukh
    Yu, Xinghuo
    2008 2ND INTERNATIONAL SYMPOSIUM ON SYSTEMS AND CONTROL IN AEROSPACE AND ASTRONAUTICS, VOLS 1 AND 2, 2008, : 333 - 336
  • [37] A Levenberg-Marquardt Algorithm for Sparse Identification of Dynamical Systems
    Haring, Mark
    Grotli, Esten Ingar
    Riemer-Sorensen, Signe
    Seel, Katrine
    Hanssen, Kristian Gaustad
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (11) : 9323 - 9336
  • [38] Parallel Levenberg-Marquardt Algorithm Without Error Backpropagation
    Bilski, Jaroslaw
    Wilamowski, Bogdan M.
    ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2017, PT I, 2017, 10245 : 25 - 39
  • [39] An inverse hull design based on Levenberg-Marquardt algorithm
    Huang, Yujia
    Feng, Baiwei
    Liu, Zuyuan
    Ship Building of China, 2014, 55 (01) : 66 - 75
  • [40] An echo state network based on Levenberg-Marquardt algorithm
    Wang, Lei
    Yang, Cuili
    Qiao, Junfei
    Wang, Gongming
    PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 3899 - 3904
12345