Implementation of neural network with approximations functions

被引：0
|
作者：
Hnatiuc, M [1 ]
Lamarque, G [1 ]
机构：
[1] Tech Univ Gh Asachi Iasi, Iasi, Romania
来源：
SCS 2003: INTERNATIONAL SYMPOSIUM ON SIGNALS, CIRCUITS AND SYSTEMS, VOLS 1 AND 2, PROCEEDINGS | 2003年
关键词：
non-linear functions; gauss function; sigmoid function; neural network;
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：
The purpose of this work is to simulate a neural network with non-linear activation functions. The non-linear functions are simulated in Microsoft Visual Studio C++ 6.0 to observe the precision and to implement on the programmable logic devices. This network is realized to accept very small input values. The multiplication between input values and weight values is realized with the add-logarithm and exponential functions. One approximates all the non-linear functions with linear functions using shift-add blocks.
引用
收藏
页码：553 / 556
页数：4
相关论文
共 50 条
  • [31] The best approximations of functions and approximations by Steklov's functions
    Lanina, EG
    VESTNIK MOSKOVSKOGO UNIVERSITETA SERIYA 1 MATEMATIKA MEKHANIKA, 2000, (02): : 49 - 52
  • [32] Dynamic research of hidden attractors in discrete memristive neural network with trigonometric functions and FPGA implementation
    Yu, Fei
    Xu, Si
    Lin, Yue
    He, Ting
    Xiao, Xiaoli
    Cai, Shuo
    Li, Yi
    EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS, 2024,
  • [33] Dynamics analysis and FPGA implementation of discrete memristive cellular neural network with heterogeneous activation functions
    Wang, Chunhua
    Luo, Dingwei
    Deng, Quanli
    Yang, Gang
    CHAOS SOLITONS & FRACTALS, 2024, 187
  • [34] Implementation of Neural Network Backpropagation in CUDA
    Liu, Jinfeng
    Guo, Lei
    INTELLIGENCE COMPUTATION AND EVOLUTIONARY COMPUTATION, 2013, 180 : 1021 - 1027
  • [35] Implementation of a Reconfigurable Neural Network in FPGA
    Oliveira, Janaina G. M.
    Moreno, Robson Luiz
    Dutra, Odilon de Oliveira
    Pimenta, Tales C.
    2017 INTERNATIONAL CARIBBEAN CONFERENCE ON DEVICES, CIRCUITS AND SYSTEMS (ICCDCS), 2017, : 41 - 44
  • [36] Efficient implementation of the THSOM neural network
    Marek, Rudolf
    Skrbek, Miroslav
    ARTIFICIAL NEURAL NETWORKS - ICANN 2008, PT II, 2008, 5164 : 159 - 168
  • [37] A Survey and Implementation on Neural Network Visualization
    Leung, Yin Chung
    Chang, Jui-Hung
    Hwang, Ren-Hung
    2018 15TH INTERNATIONAL SYMPOSIUM ON PERVASIVE SYSTEMS, ALGORITHMS AND NETWORKS (I-SPAN 2018), 2018, : 107 - 112
  • [38] Optical implementation of the Kak neural network
    Shortt, A
    Keating, JG
    Moulinier, L
    Pannell, CN
    INFORMATION SCIENCES, 2005, 171 (1-3) : 273 - 287
  • [39] Framework for neural network hardware implementation
    Brassai, Sandor Tihamer
    Hammas, Attila
    Bustya, Balazs
    2022 23RD INTERNATIONAL CARPATHIAN CONTROL CONFERENCE (ICCC), 2022, : 387 - 391
  • [40] Neural network implementation of the BCJR algorithm
    Sazli, Murat Husnu
    Isik, Can
    DIGITAL SIGNAL PROCESSING, 2007, 17 (01) : 353 - 359
12345