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
  • [21] Modified gradient-based learning for local coupled feedforward neural networks with Gaussian basis function
    Qu, Yanpeng
    Shang, Changjing
    Yang, Jie
    Wu, Wei
    Shen, Qiang
    NEURAL COMPUTING & APPLICATIONS, 2013, 22 : S379 - S394
  • [22] Modified gradient-based learning for local coupled feedforward neural networks with Gaussian basis function
    Yanpeng Qu
    Changjing Shang
    Jie Yang
    Wei Wu
    Qiang Shen
    Neural Computing and Applications, 2013, 22 : 379 - 394
  • [23] An immune and a gradient-based method to train multi-layer perceptron neural networks
    Pasti, Rodrigo
    de Castro, Leandro Nunes
    2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 2075 - +
  • [24] Overfitting and neural networks: Conjugate gradient and backpropagation
    Lawrence, S
    Giles, CL
    IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL I, 2000, : 114 - 119
  • [25] Stability analysis of gradient-based neural networks for optimization problems
    Han, QM
    Liao, LZ
    Qi, HD
    Qi, LQ
    JOURNAL OF GLOBAL OPTIMIZATION, 2001, 19 (04) : 363 - 381
  • [26] Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-based optimization to spiking neural networks
    Neftci, Emre O.
    Mostafa, Hesham
    Zenke, Friedemann
    IEEE SIGNAL PROCESSING MAGAZINE, 2019, 36 (06) : 51 - 63
  • [27] Stability Analysis of Gradient-Based Neural Networks for Optimization Problems
    Qiaoming Han
    Li-Zhi Liao
    Houduo Qi
    Liqun Qi
    Journal of Global Optimization, 2001, 19 : 363 - 381
  • [28] Correcting gradient-based interpretations of deep neural networks for genomics
    Antonio Majdandzic
    Chandana Rajesh
    Peter K. Koo
    Genome Biology, 24
  • [29] Correcting gradient-based interpretations of deep neural networks for genomics
    Majdandzic, Antonio
    Rajesh, Chandana
    Koo, Peter K.
    GENOME BIOLOGY, 2023, 24 (01)
  • [30] An Efficient non-Backpropagation Method for Training Spiking Neural Networks
    Guo, Shiqi
    Lin, Tong
    2021 IEEE 33RD INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2021), 2021, : 192 - 199
12345