Pulse density Hopfield Neural Network system with learning capability using FPGA

被引：0
|
作者：
Maeda, Yutaka [1 ]
Fukuda, Yoshinori [1 ]
机构：
[1] Kansai Univ, Dept Elect & Elect Engn, 3-3-35 Yamate Cho, Suita, Osaka 5648680, Japan
来源：
COMPUTATIONAL METHODS AND APPLIED COMPUTING | 2008年
关键词：
hardware implementation; pulse density; HNN; learning; simultaneous perturbation; FPGA;
D O I：
暂无
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In this paper, we present a FPGA Hopfield Neural Network system with learning capability using the simultaneous perturbation learning rule. In the neural network, outputs and internal values are represented by pulse train. That is, analog Hopfield Neural Network with pulse frequency representation is considered. The pulse density representation and the simultaneous perturbation enable the system with learning capability to easily implement as a hardware system. Details of the design are described. Analog and digital examples are also shown to confirm a viability of the system configuration and the learning capability.
引用
收藏
页码：320 / +
页数：2
相关论文
共 50 条
  • [21] Learning algorithms for a neural network in FPGA
    Aoyama, T
    Wang, QY
    Suematsu, R
    Shimizu, R
    Nagashima, U
    [J]. PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1007 - 1012
  • [22] Simultaneous perturbation learning rule for Hopfield neural network
    Itonaga, S
    Maeda, Y
    [J]. KNOWLEDGE-BASED INTELLIGENT INFORMATION ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, PTS 1 AND 2, 2001, 69 : 171 - 174
  • [23] FPGA implementation of programmable pulse mode neural network with on chip learning for signature application
    Krid, Mohamed
    Dammak, Alima
    Masmoudi, Dorra Sellami
    [J]. 2006 13TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS, VOLS 1-3, 2006, : 942 - 945
  • [24] Structural analysis by using Hopfield neural network
    Wei, Pengsheng
    [J]. Huaqiao Daxue Xuebao/Journal of Huaqiao University, 20 (02): : 146 - 149
  • [25] Security dispatch using the Hopfield neural network
    Yalcinoz, T
    Short, MJ
    Cory, BJ
    [J]. IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION, 1999, 146 (05) : 465 - 470
  • [26] A new type of pulse neural network based on FPGA
    Huang, Qian
    Li, WenLong
    Kang, Jian
    Yang, Jun
    [J]. MECHATRONICS ENGINEERING, COMPUTING AND INFORMATION TECHNOLOGY, 2014, 556-562 : 6081 - 6084
  • [27] FPGA based implementation of a Hopfield neural network for solving constraint satisfaction problems
    Abramson, D
    Smith, K
    Logothetis, P
    Duke, D
    [J]. 24TH EUROMICRO CONFERENCE - PROCEEDING, VOLS 1 AND 2, 1998, : 688 - 693
  • [28] Simplified Discrete Two-Neuron Hopfield Neural Network and FPGA Implementation
    Bao, Bocheng
    Tang, Haigang
    Bao, Han
    Hua, Zhongyun
    Xu, Quan
    Chen, Mo
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2024,
  • [29] LIMITING THE RECONSTRUCTION CAPABILITY OF GENERATIVE NEURAL NETWORK USING NEGATIVE LEARNING
    Munawar, Asim
    Vinayavekhin, Phongtharin
    De Magistris, Giovanni
    [J]. 2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2017,
  • [30] Approximation and decomposition of attractors of a Hopfield neural network system
    Danca, Marius-F.
    Chen, Guanrong
    [J]. CHAOS SOLITONS & FRACTALS, 2024, 186
12345