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
  • [21] Collecting the Database for the Neural Network Deep Learning Implementation
    Isaeva, Ekaterina
    Bakhtin, Vadim
    Tararkov, Andrey
    DIGITAL SCIENCE, 2019, 850 : 12 - 18
  • [22] Research and Implementation for PGS Based On BP Neural Network
    Sun, Yong
    Liao, Lili
    Wang, Jian
    Zhang, Shukuei
    Zhang, Maoqing
    CJCM: 5TH CHINA-JAPAN CONFERENCE ON MECHATRONICS 2008, 2008, : 171 - 175
  • [23] High accuracy inference by an optical neural network implementation
    Miura, Shun
    Otake, Mamoru
    Kusaka, Hiroyuki
    Kashiwagi, Masahiro
    Kunai, Yuichiro
    Nambara, Takahiro
    Yamada, Yumi
    SPIE FUTURE SENSING TECHNOLOGIES 2023, 2023, 12327
  • [24] Epilepsy Identification System with Neural Network Hardware Implementation
    Tsou, Chieh
    Liao, Chi-Chung
    Lee, Shuenn-Yuh
    2019 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2019), 2019, : 163 - 166
  • [25] Design and implementation of a random neural network routing engine
    Kocak, T
    Seeber, J
    Terzioglu, H
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (05): : 1128 - 1143
  • [26] Neural Network Based Attack on a Masked Implementation of AES
    Gilmore, Richard
    Hanley, Neil
    O'Neill, Maire
    2015 IEEE INTERNATIONAL SYMPOSIUM ON HARDWARE ORIENTED SECURITY AND TRUST (HOST), 2015, : 106 - 111
  • [27] Digital Recognition Based on Neural Network and FPGA Implementation
    Zhang, Chaoyue
    Wang, Yu
    Guo, Jinxu
    Zhang, Hao
    2017 NINTH INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS (IHMSC 2017), VOL 1, 2017, : 280 - 283
  • [28] Design and implementation of neural network adaptive inverse control
    Yu, Shuang
    Liu, Guohai
    Mei, Congli
    Ding, Yuhan
    Jiang, Hui
    Journal of Convergence Information Technology, 2012, 7 (10) : 272 - 278
  • [29] Neural network with unbounded activation functions is universal approximator
    Sonoda, Sho
    Murata, Noboru
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2017, 43 (02) : 233 - 268
  • [30] Fusion of Chaotic Activation Functions in Training Neural Network
    Kabir, A. N. M. Enamul
    Uddin, A. F. M. Nokib
    Asaduzzaman, M.
    Hasan, M. Fahad
    Hasan, M. Imran
    Shahjahan, Md
    2012 7TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (ICECE), 2012,
12345