An analysis of learning algorithm for layered neural network with coupled gradient descent method

被引：0
|
作者：
Isokawa, T [1 ]
Matsui, N [1 ]
机构：
[1] Himeji Inst Technol, Dept Comp Engn, Himeji, Hyogo 67122, Japan
来源：
8TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING, VOLS 1-3, PROCEEDING | 2001年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A new learning method of layered neural network is proposed in this paper. This method uses two networks that have same structures and different initial conditions. In these two networks, neurons of one network updates their weights not only by using their own information and but information of the other network, and vice versa. This method, collaboration and competition between networks, can be efficient for avoiding local minima. We explore efficiency of this method quantitatively through applying it to XOR and 4bit parity check problems.
引用
收藏
页码：751 / 754
页数：4
相关论文
共 50 条
  • [1] A neural network incorporating coupled gradient descent method
    Isokawa, T
    Matsui, N
    Peper, F
    [J]. KNOWLEDGE-BASED INTELLIGENT INFORMATION ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, PTS 1 AND 2, 2001, 69 : 162 - 165
  • [2] An approximate gradient descent algorithm for Spiking Neural Network
    Chen, Wenjie
    Li, Chuandong
    [J]. 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 4690 - 4694
  • [3] A gradient descent learning algorithm for fuzzy neural networks
    Feuring, T
    Buckley, JJ
    Hayashi, Y
    [J]. 1998 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AT THE IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE - PROCEEDINGS, VOL 1-2, 1998, : 1136 - 1141
  • [4] Network Gradient Descent Algorithm for Decentralized Federated Learning
    Wu, Shuyuan
    Huang, Danyang
    Wang, Hansheng
    [J]. JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2023, 41 (03) : 806 - 818
  • [5] Learning in a layered neural network by the Hamiltonian algorithm
    Kohno, Y
    [J]. ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 2620 - 2624
  • [6] Gradient learning algorithm for ensembling neural network
    Meng, Jiang
    An, Kun
    [J]. 2006 9TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION, VOLS 1- 5, 2006, : 1658 - +
  • [7] Learning algorithm for Pulse Coupled Neural Network
    Calvin, P
    Yuen, G
    Boddruzzaman, M
    Malkani, M
    [J]. THIRTIETH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY (SSST), 1998, : 407 - 411
  • [8] Learning gradients by a gradient descent algorithm
    Dong, Xuemei
    Zhou, Ding-Xuan
    [J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2008, 341 (02) : 1018 - 1027
  • [9] A learning algorithm for tuning fuzzy rules based on the gradient descent method
    Shi, Y
    Mizumoto, M
    Yubazaki, N
    Otani, M
    [J]. FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 55 - 61
  • [10] Hopfield neural network learning using direct gradient descent of energy function
    Tang, Z
    Tashima, K
    Hebishima, H
    Ishizuka, O
    Tanno, K
    [J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1996, E79A (02) : 258 - 261
12345