Variable projection method and levenberg-marquardt algorithm for neural network training

被引：0
|
作者：
Kim, Cheol-Taek [1 ]
Lee, Ju-Jang [1 ]
Kim, Hyejin [2 ]
机构：
[1] Korea Adv Inst Sci & Technol, 373-1,Kuseongdong, Taejon 305701, South Korea
[2] ETRI, Taejon, South Korea
来源：
IECON 2006 - 32ND ANNUAL CONFERENCE ON IEEE INDUSTRIAL ELECTRONICS, VOLS 1-11 | 2006年
关键词：
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
An optimal solution for single hidden layered feedforward neural network(SLFN) is proposed. SLFN can be considered as separable nonlinear least squares problem and variable projection(VP) method gives the approximation of the jacobian matrix of the problem. The jacobian calculation of VP-SLFN is suggested with simplified form. Based on this simplification, Levenberg-Marquardt(LM) algorithm for VP-SLFN is suggested and has faster convergence rate than LM algorithm without VP. Two numerical examples show the superiority than extreme learning machine and LM without variable projection.
引用
收藏
页码：2084 / +
页数：2
相关论文
共 50 条
  • [11] Application of Levenberg-Marquardt method to the training of spiking neural networks
    Silva, SM
    Ruano, AE
    PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND BRAIN, VOLS 1-3, 2005, : 1354 - 1358
  • [12] Acceleration of Levenberg-Marquardt training of neural networks with variable decay rate
    Chen, TC
    Han, DJ
    Francis, FTK
    Tham, LG
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 1873 - 1878
  • [13] GPU implementation of the feedforward neural network with modified Levenberg-Marquardt algorithm
    Tomislav, Bacek
    Majetic, Dubravko
    Brezak, Danko
    Proceedings of the International Joint Conference on Neural Networks, 2014, : 785 - 791
  • [14] Performance of Levenberg-Marquardt Neural Network Algorithm in Air Quality Forecasting
    Mun, Cho Kar
    Abd Rahman, Nur Haizum
    Ilias, Iszuanie Syafidza Che
    SAINS MALAYSIANA, 2022, 51 (08): : 2645 - 2654
  • [15] Accelerated Levenberg-Marquardt Algorithm for Radial Basis Function Neural Network
    Ma Miaoli
    Wu Xiaolong
    Han Honggui
    2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 6804 - 6809
  • [16] GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm
    Tomislav, Bacek
    Majetic, Dubravko
    Brezak, Danko
    PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 785 - 791
  • [17] Levenberg-Marquardt Training Algorithms for Random Neural Networks
    Basterrech, Sebastian
    Mohammed, Samir
    Rubino, Gerardo
    Soliman, Mostafa
    COMPUTER JOURNAL, 2011, 54 (01): : 125 - 135
  • [18] Combining Genetic Algorithm and Levenberg-Marquardt Algorithm in Training Neural Network for Hypoglycemia Detection using EEG Signals
    Nguyen, Lien B.
    Nguyen, Anh V.
    Ling, Sai Ho
    Nguyen, Hung T.
    2013 35TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2013, : 5386 - 5389
  • [19] Parallel and separable recursive Levenberg-Marquardt training algorithm
    Asirvadam, VS
    McLoone, SF
    Irwin, GW
    NEURAL NETWORKS FOR SIGNAL PROCESSING XII, PROCEEDINGS, 2002, : 129 - 138
  • [20] Fast Computational Approach to the Levenberg-Marquardt Algorithm for Training Feedforward Neural Networks
    Bilski, Jaroslaw
    Smolag, Jacek
    Kowalczyk, Bartosz
    Grzanek, Konrad
    Izonin, Ivan
    JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH, 2023, 13 (02) : 45 - 61
12345