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
  • [41] Application of an improved Levenberg-Marquardt back propagation neural network to gear fault level identification
    Zhang, Xinghui
    Xiao, Lei
    Kang, Jianshe
    JOURNAL OF VIBROENGINEERING, 2014, 16 (02) : 855 - 868
  • [42] Brain tumour detection in magnetic resonance imaging using Levenberg-Marquardt backpropagation neural network
    Ghahramani, Marzieh
    Shiri, Nabiollah
    IET IMAGE PROCESSING, 2023, 17 (01) : 88 - 103
  • [43] Transient signal analysis based on Levenberg-Marquardt method for fault feature extraction of rotating machines
    Wang, Shibin
    Cai, Gaigai
    Zhu, Zhongkui
    Huang, Weiguo
    Zhang, Xingwu
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2015, 54-55 : 16 - 40
  • [44] Efficient Industrial Robot Calibration via a Novel Unscented Kalman Filter-Incorporated Variable Step-Size Levenberg-Marquardt Algorithm
    Li, Zhibin
    Li, Shuai
    Luo, Xin
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [45] Damage reconstruction of 3D frames using genetic algorithms with Levenberg-Marquardt local search
    Kokot, Seweryn
    Zembaty, Zbigniew
    SOIL DYNAMICS AND EARTHQUAKE ENGINEERING, 2009, 29 (02) : 311 - 323
  • [46] Landslide susceptibility assessment in the Hoa Binh province of Vietnam: A comparison of the Levenberg-Marquardt and Bayesian regularized neural networks
    Dieu Tien Bui
    Pradhan, Biswajeet
    Lofman, Owe
    Revhaug, Inge
    Dick, Oystein B.
    GEOMORPHOLOGY, 2012, 171 : 12 - 29
  • [47] A modified Levenberg-Marquardt algorithm for simultaneous estimation of multi-parameters of boundary heat flux by solving transient nonlinear inverse heat conduction problems
    Cui, Miao
    Yang, Kai
    Xu, Xiao-liang
    Wang, Sheng-dong
    Gao, Xiao-wei
    INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 2016, 97 : 908 - 916
  • [48] Estimation of flexible riser curvature distribution and bend stiffener polyurethane behavior using the Levenberg-Marquardt algorithm in full scale bending-tension tests
    He, Yangye
    Hernandez, Irving David
    Vaz, Murilo Augusto
    Caire, Marcelo
    OCEAN ENGINEERING, 2020, 216
  • [49] Short-term price forecasting of Nordic power market by combination Levenberg-Marquardt and Cuckoo search algorithms
    Kim, Mun Kyeom
    IET GENERATION TRANSMISSION & DISTRIBUTION, 2015, 9 (13) : 1553 - 1563
  • [50] An anti-phishing enterprise environ model using feed-forward backpropagation and Levenberg-Marquardt method
    Sankhwar, Shweta
    Pandey, Dhirendra
    Khan, Raees Ahmad
    Mohanty, Sachi Nandan
    SECURITY AND PRIVACY, 2021, 4 (01)
12345