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] Neural network approximations for Calabi-Yau metrics
    Vishnu Jejjala
    Damián Kaloni Mayorga Peña
    Challenger Mishra
    Journal of High Energy Physics, 2022
  • [22] Latitudinal and longitudinal neural network structures for function approximations
    Chen, DG
    Mohler, RR
    ICECS 96 - PROCEEDINGS OF THE THIRD IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS, AND SYSTEMS, VOLS 1 AND 2, 1996, : 283 - 286
  • [23] EXISTENCE AND UNIQUENESS RESULTS FOR NEURAL-NETWORK APPROXIMATIONS
    WILLIAMSON, RC
    HELMKE, U
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (01): : 2 - 13
  • [24] Video compression with wavelets and random neural network approximations
    Hai, F
    Hussain, K
    Gelenbe, E
    Guha, R
    APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN IMAGE PROCESSING VI, 2001, 4305 : 57 - 64
  • [25] Investigation on practical possibility of function approximations by neural network
    Yang, Xiaohui
    Chen, Dingguo
    System and Control: Theory and Applications, 2000, : 293 - 298
  • [26] Best k-Layer Neural Network Approximations
    Lim, Lek-Heng
    Michalek, Mateusz
    Qi, Yang
    CONSTRUCTIVE APPROXIMATION, 2022, 55 (01) : 583 - 604
  • [27] Symmetric table addition methods for neural network approximations
    Koc-Sahan, N
    Schlessman, JA
    Schulte, MJ
    ADVANCED SIGNAL PROCESSING ALGORITHMS, ARCHITECTURES, AND IMPLEMENTATIONS XI, 2001, 4474 : 126 - 133
  • [28] Comparing neural network approximations for different functional forms
    Morgan, P
    Curry, B
    Beynon, M
    EXPERT SYSTEMS, 1999, 16 (02) : 60 - 71
  • [29] SIGMOIDAL APPROXIMATIONS OF A DELAY NEURAL LATTICE MODEL WITH HEAVISIDE FUNCTIONS
    Wang, Xiaoli
    Yang, Meihua
    Kloeden, Peter E.
    COMMUNICATIONS ON PURE AND APPLIED ANALYSIS, 2020, 19 (04) : 2385 - 2402
  • [30] Conversion of Artificial Neural Network to Spiking Neural Network for Hardware Implementation
    Chen, Yi-Lun
    Lu, Chih-Cheng
    Juang, Kai-Cheung
    Tang, Kea-Tiong
    2019 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TW), 2019,
12345