Improved training rules for multilayered feedforward neural networks

被引：2
|
作者：
Sung, SW
Lee, TY
Park, S
机构：
[1] Korea Adv Inst Sci & Technol, Dept Chem & Biomol Engn, Yuseong Gu, Taejon 305701, South Korea
[2] Korea Adv Inst Sci & Technol, Ctr Ultramicrochem Proc Syst, Yuseong Gu, Taejon 305701, South Korea
来源：
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH | 2003年 / 42卷 / 06期
关键词：
D O I：
10.1021/ie020663k
中图分类号：
TQ [化学工业];
学科分类号：
0817 ;
摘要：
We propose an improved supervisory training rule for multilayered feedforward neural networks (FNNs). The proposed method analytically estimates the optimal solutions for the output weights of FNNs. Also, using the optimal solutions, it reduces the searching space as much as the output weights in the iterative high-dimensional nonlinear optimization problem for the supervisory training. As a result, we can secure a much faster convergence rate and better robustness compared to the previous full-dimensional training rules.
引用
收藏
页码：1275 / 1278
页数：4
相关论文
共 50 条
  • [31] Evolutional design and training algorithm for feedforward neural networks
    Takahashi, H
    Nakajima, M
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1999, E82D (10) : 1384 - 1392
  • [32] A global optimization algorithm for training feedforward neural networks
    Huanqin Li
    [J]. DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2006, 13 : 846 - 849
  • [33] On H∞ filtering in feedforward neural networks training and pruning
    Tang, He-Sheng
    Xue, Song-Tao
    Chen, Rong
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 515 - 523
  • [34] A fast learning algorithm for training feedforward neural networks
    Goel, Ashok Kumar
    Saxena, Suresh C.
    Bhanot, Surekha
    [J]. INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2006, 37 (10) : 709 - 722
  • [35] A modified backpropagation training algorithm for feedforward neural networks
    Kathirvalavakumar, T
    Thangavel, P
    [J]. NEURAL PROCESSING LETTERS, 2006, 23 (02) : 111 - 119
  • [36] THE UD RLS ALGORITHM FOR TRAINING FEEDFORWARD NEURAL NETWORKS
    Bilski, Jaroslaw
    [J]. INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2005, 15 (01) : 115 - 123
  • [37] A parallel algorithm for gradient training of feedforward neural networks
    Hanzalek, Z
    [J]. PARALLEL COMPUTING, 1998, 24 (5-6) : 823 - 839
  • [38] A Modified Backpropagation Training Algorithm for Feedforward Neural Networks*
    T. Kathirvalavakumar
    P. Thangavel
    [J]. Neural Processing Letters, 2006, 23 : 111 - 119
  • [39] Separable recursive training algorithms for feedforward neural networks
    Asirvadam, VS
    McLoone, SF
    Irwin, GW
    [J]. PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1212 - 1217
  • [40] Taming the Reservoir: Feedforward Training for Recurrent Neural Networks
    Obst, Oliver
    Riedmiller, Martin
    [J]. 2012 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2012,
12345