Parallel Levenberg-Marquardt Algorithm Without Error Backpropagation

被引：10
|
作者：
Bilski, Jaroslaw [1 ]
Wilamowski, Bogdan M. [2 ]
机构：
[1] Czestochowa Tech Univ, Inst Computat Intelligence, Czestochowa, Poland
[2] Auburn Univ, Auburn, AL 36849 USA
来源：
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2017, PT I | 2017年 / 10245卷
关键词：
Forward-only computation; Neural network training; Parallel architectures; REALIZATION; NETWORKS;
D O I：
10.1007/978-3-319-59063-9_3
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents a new parallel architecture of the Levenberg-Marquardt (LM) algorithm for training fully connected feedforward neural networks, which will also work for MLP but some cells will stay empty. This approach is based on a very interesting idea of learning neural networks without error backpropagation. The presented architecture is based on completely new parallel structures to significantly reduce a very high computational load of the LM algorithm. A full explanation of parallel three-dimensional neural network learning structures is provided.
引用
收藏
页码：25 / 39
页数：15
相关论文
共 50 条
  • [11] Automated Real Time Video Quality Measurement Using Levenberg-Marquardt Backpropagation Algorithm
    Archana, P.
    Kulkarni, Subhash
    [J]. 2014 FIFTH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP 2014), 2014, : 348 - 353
  • [12] Predicting International Roughness Index by Deep Neural Networks with Levenberg-Marquardt backpropagation learning algorithm
    Fiorentini, Nicholas
    Leandri, Pietro
    Losa, Massimo
    [J]. EARTH RESOURCES AND ENVIRONMENTAL REMOTE SENSING/GIS APPLICATIONS XII, 2021, 11863
  • [13] Distributed localization using Levenberg-Marquardt algorithm
    Shervin Parvini Ahmadi
    Anders Hansson
    Sina Khoshfetrat Pakazad
    [J]. EURASIP Journal on Advances in Signal Processing, 2021
  • [14] Parameter identification of proton exchange membrane fuel cell via Levenberg-Marquardt backpropagation algorithm
    Yang, Bo
    Zeng, Chunyuan
    Wang, Long
    Guo, Yinyuan
    Chen, Guanghua
    Guo, Zhengxun
    Chen, Yijun
    Li, Danyang
    Cao, Pulin
    Shu, Hongchun
    Yu, Tao
    Zhu, Jiawei
    [J]. INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2021, 46 (44) : 22998 - 23012
  • [15] Application of backpropagation neural network based on levenberg-marquardt algorithm in detection of fraudulent financial statements
    Deng Qingshan
    Mei Guoping
    [J]. ADVANCED COMPUTER TECHNOLOGY, NEW EDUCATION, PROCEEDINGS, 2007, : 151 - 154
  • [16] Aspheric Surface Shape Error Correction Based on Modified Levenberg-Marquardt Algorithm
    Deng Jiannan
    Wang Han
    Yao Honghui
    Zhang Jiarong
    Zhuo Shaomu
    Yan Xiaoqiang
    [J]. ACTA OPTICA SINICA, 2022, 42 (05)
  • [17] Convergence analysis of a subsampled Levenberg-Marquardt algorithm
    Xing, Ganchen
    Gu, Jian
    Xiao, Xiantao
    [J]. OPERATIONS RESEARCH LETTERS, 2023, 51 (04) : 379 - 384
  • [18] A Levenberg-Marquardt algorithm for unconstrained multicriteria optimization
    Fischer, Andreas
    Shukla, Pradyumn K.
    [J]. OPERATIONS RESEARCH LETTERS, 2008, 36 (05) : 643 - 646
  • [19] Distributed localization using Levenberg-Marquardt algorithm
    Ahmadi, Shervin Parvini
    Hansson, Anders
    Pakazad, Sina Khoshfetrat
    [J]. EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2021, 2021 (01)
  • [20] A Parallel Levenberg-Marquardt Algorithm for Recursive Neural Network in a Robot Control System
    Wang, Wei
    Pu, Yunming
    Li, Wang
    [J]. INTERNATIONAL JOURNAL OF COGNITIVE INFORMATICS AND NATURAL INTELLIGENCE, 2018, 12 (02) : 32 - 47
12345