HDL design of pulse density neural network using simultaneous perturbation

被引：0
|
作者：
Maeda, Y [1 ]
Tada, T [1 ]
Kanata, Y [1 ]
机构：
[1] Kansai Univ, Fac Engn, Dept Elect Engn, Suita, Osaka 564, Japan
来源：
ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3 | 1998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：
In this paper, we present HDL design of a pulse density neural network circuit with learning ability. We use the simultaneous perturbation method as a learning rule. The learning rule requires only twice forward operations of networks. Thus, without complicated circuit that calculates gradients of an error function, we could construct the network system with learning ability. We designed a pulse density neural network using VHDL. At the same time, we confirmed simulation results of the design through the exclusive OR problem and simple function learning problem.
引用
收藏
页码：81 / 84
页数：4
相关论文
共 50 条
  • [1] FPGA implementation of a pulse density neural network using simultaneous perturbation
    Maeda, Y
    Tada, T
    IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III, 2000, : 296 - 301
  • [2] Pulse density neural network system using simultaneous perturbation learning rule
    Maeda, Y
    Nakazawa, A
    Kanata, Y
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 980 - 984
  • [3] Hardware Implementation of a Pulse Density Neural Network Using Simultaneous Perturbation Learning Rule
    Yutaka Maeda
    Atsushi Nakazawa
    Yakichi Kanata
    Analog Integrated Circuits and Signal Processing, 1999, 18 : 153 - 162
  • [4] Hardware implementation of a pulse density neural network using simultaneous perturbation learning rule
    Maeda, Y
    Nakazawa, A
    Kanata, Y
    ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 1999, 18 (2-3) : 153 - 162
  • [5] FPGA implementation of a pulse density neural network with learning ability using simultaneous perturbation
    Maeda, Y
    Tada, T
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (03): : 688 - 695
  • [6] An analog neural network system with learning capability using simultaneous perturbation
    Maeda, Y
    Kusuhashi, T
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1999, E82D (12) : 1627 - 1633
  • [7] Active noise control using neural network with the simultaneous perturbation learning rule
    Tsuyama, Y
    Maeda, Y
    SICE 2002: PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, VOLS 1-5, 2002, : 1633 - 1634
  • [8] Robust neural network tracking controller using simultaneous perturbation stochastic approximation
    Song, Qing
    Spall, James C.
    Soh, Yeng Chai
    Ni, Jie
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (05): : 817 - 835
  • [9] Robust neural network tracking controller using simultaneous perturbation stochastic approximation
    Song, Q
    Spall, JC
    Soh, YC
    42ND IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-6, PROCEEDINGS, 2003, : 6194 - 6199
  • [10] Simultaneous perturbation learning rule for Hopfield neural network
    Itonaga, S
    Maeda, Y
    KNOWLEDGE-BASED INTELLIGENT INFORMATION ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, PTS 1 AND 2, 2001, 69 : 171 - 174
12345