A Modified Gradient-based Backpropagation Training Method for Neural Networks

被引：0
|
作者：
Mu, Xuewen [1 ]
Zhang, Yaling [2 ]
机构：
[1] Xidian Univ, Dept Appl Math, Xian 710071, Peoples R China
[2] Xian Sci & Technol Univ, Dept Comp Sci, Xian 710054, Peoples R China
来源：
2009 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING ( GRC 2009) | 2009年
关键词：
Barzilai and Borwein steplength; Resilient Propagation method; backpropagation training method;
D O I：
10.1109/GRC.2009.5255081
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A improved gradient-based backpropagation training method is proposed for neural networks in this paper. Based on the Barzilai and Borwein steplength update and some technique of Resilient Propagation method, we adapt the new learning rate to improves the speed and the success rate. Experimental results show that the proposed method has considerably improved convergence speed, and for the chosen test problems, outperforms other well-known training methods.
引用
收藏
页码：450 / +
页数：2
相关论文
共 50 条
  • [31] A Gradient-Interleaved Scheduler for Energy-Efficient Backpropagation for Training Neural Networks
    Unnikrishnan, Nanda
    Parhi, Keshab K.
    2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
  • [32] Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks
    Kathirvalavakumar, T.
    Subavathi, S. Jeyaseeli
    NEUROCOMPUTING, 2009, 72 (16-18) : 3915 - 3921
  • [33] AN ADAPTIVE TRAINING ALGORITHM FOR BACKPROPAGATION NEURAL NETWORKS
    HSIN, HC
    LI, CC
    SUN, MG
    SCLABASSI, RJ
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1995, 25 (03): : 512 - 514
  • [34] Accelerating Training of Large Neural Models by Gradient-Based Growth Learning
    Jiang, Haowei
    Yu, Jianxing
    Zheng, Libin
    Zhu, Huaijie
    Liu, Wei
    Yin, Jian
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2024, PT 2, 2025, 14851 : 19 - 34
  • [35] A stochastic backpropagation algorithm for training neural networks
    Chen, YQ
    Yin, T
    Babri, HA
    ICICS - PROCEEDINGS OF 1997 INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATIONS AND SIGNAL PROCESSING, VOLS 1-3: THEME: TRENDS IN INFORMATION SYSTEMS ENGINEERING AND WIRELESS MULTIMEDIA COMMUNICATIONS, 1997, : 703 - 707
  • [36] IMPROVEMENT OF THE BACKPROPAGATION ALGORITHM FOR TRAINING NEURAL NETWORKS
    LEONARD, J
    KRAMER, MA
    COMPUTERS & CHEMICAL ENGINEERING, 1990, 14 (03) : 337 - 341
  • [37] Comparison of Backpropagation and Kalman Filter-based Training for Neural Networks
    Luttmann, Laurin
    Mercorelli, Paolo
    2021 25TH INTERNATIONAL CONFERENCE ON SYSTEM THEORY, CONTROL AND COMPUTING (ICSTCC), 2021, : 234 - 241
  • [38] Understanding the Convolutional Neural Networks with Gradient Descent and Backpropagation
    Zhou, XueFei
    2ND INTERNATIONAL CONFERENCE ON MACHINE VISION AND INFORMATION TECHNOLOGY (CMVIT 2018), 2018, 1004
  • [39] A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks
    Khan, Shujaat
    Ahmad, Jawwad
    Naseem, Imran
    Moinuddin, Muhammad
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2018, 37 (02) : 593 - 612
  • [40] A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks
    Shujaat Khan
    Jawwad Ahmad
    Imran Naseem
    Muhammad Moinuddin
    Circuits, Systems, and Signal Processing, 2018, 37 : 593 - 612
12345