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
  • [41] INVESTIGATION OF ANALYSIS AND GRADIENT-BASED DESIGN OPTIMIZATION USING NEURAL NETWORKS
    Fuchi, Kazuko W.
    Wolf, Eric M.
    Makhija, David S.
    Wukie, Nathan A.
    Schrock, Christopher R.
    Beran, Philip S.
    PROCEEDINGS OF THE ASME 2020 CONFERENCE ON SMART MATERIALS, ADAPTIVE STRUCTURES AND INTELLIGENT SYSTEMS (SMASIS2020), 2020,
  • [42] Gradient-based neural networks for solving periodic Sylvester matrix equations
    Lv, Lingling
    Chen, Jinbo
    Zhang, Lei
    Zhang, Fengrui
    JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2022, 359 (18): : 10849 - 10866
  • [43] Differentiable Oscillators in Recurrent Neural Networks for Gradient-Based Sequence Modeling
    Otte, Sebastian
    Butz, Martin V.
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, PT II, 2017, 10614 : 745 - 746
  • [44] Controlling Robot Manipulators Using Gradient-Based Recursive Neural Networks
    Tan, Ning
    Zhang, Mao
    Yu, Peng
    2020 INTERNATIONAL SYMPOSIUM ON AUTONOMOUS SYSTEMS (ISAS), 2020, : 207 - 211
  • [45] Momentum gradient-based untargeted poisoning attack on hypergraph neural networks
    Chen, Yang
    Picek, Stjepan
    Ye, Zhonglin
    Wang, Zhaoyang
    Zhao, Haixing
    NEUROCOMPUTING, 2025, 634
  • [46] Improved variable-step backpropagation training method for feedforward neural networks
    Cogswell, R
    INTERNATIONAL SOCIETY FOR COMPUTERS AND THEIR APPLICATIONS 13TH INTERNATIONAL CONFERENCE ON COMPUTERS AND THEIR APPLICATIONS, 1998, : 330 - 335
  • [47] A new conjugate gradient algorithm for training neural networks based on a modified secant equation
    Livieris, Ioannis E.
    Pintelas, Panagiotis
    APPLIED MATHEMATICS AND COMPUTATION, 2013, 221 : 491 - 502
  • [48] Hardware implementation of backpropagation using progressive gradient descent for in situ training of multilayer neural networks
    van Doremaele, Eveline R. W.
    Stevens, Tim
    Ringeling, Stijn
    Spolaor, Simone
    Fattori, Marco
    van de Burgt, Yoeri
    SCIENCE ADVANCES, 2024, 10 (28):
  • [49] Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search
    Shu, Yao
    Dai, Zhongxiang
    Wu, Zhaoxuan
    Low, Bryan Kian Hsiang
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [50] Differentiable plasticity: training plastic neural networks with backpropagation
    Miconi, Thomas
    Clune, Jeff
    Stanley, Kenneth O.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
12345