The Effects of Precision Constraints in a Backpropagation Learning Network

被引：44
|
作者：
Hollis, Paul W. [1 ]
Harper, John S. [1 ]
Paulos, John J. [1 ]
机构：
[1] North Carolina State Univ, Dept Elect & Comp Engn, Raleigh, NC 27695 USA
来源：
NEURAL COMPUTATION | 1990年 / 2卷 / 03期
关键词：
D O I：
10.1162/neco.1990.2.3.363
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents a study of precision constraints imposed by a hybrid chip architecture with analog neurons and digital backpropagation calculations. Conversions between the analog and digital domains and weight storage restrictions impose precision limits on both analog and digital calculations. It is shown through simulations that a learning system of this nature can be implemented in spite of limited resolution in the analog circuits and using fixed point arithmetic to implement the backpropagation algorithm.
引用
收藏
页码：363 / 373
页数：11
相关论文
共 50 条
  • [1] Effects of the polarity of neural network units on backpropagation learning
    Gotanda, H
    Ueda, Y
    Kawasaki, T
    SYSTEMS AND COMPUTERS IN JAPAN, 1996, 27 (14) : 55 - 67
  • [2] Learning nonlinear constraints with contrastive backpropagation
    Mnih, A
    Hinton, G
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 1302 - 1307
  • [3] Improving backpropagation learning under limited precision
    Babri, HA
    Chen, YQ
    Yin, T
    PATTERN RECOGNITION LETTERS, 1998, 19 (11) : 1007 - 1016
  • [4] Neural Network Learning without Backpropagation
    Wilamowski, Bogdan M.
    Yu, Hao
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2010, 21 (11): : 1793 - 1803
  • [5] The effects of quantization on the backpropagation learning
    Ikeda, K
    Suzuki, A
    Nakayama, K
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1896 - 1900
  • [6] Softprop: Softmax neural network backpropagation learning
    Rimer, M
    Martinez, T
    2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 979 - 983
  • [7] A concept learning network based on correlation and backpropagation
    Fu, LM
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1999, 29 (06): : 912 - 916
  • [8] LEARNING PERCEPTRON NEURAL NETWORK WITH BACKPROPAGATION ALGORITHM
    Ruxanda, Gheorghe
    ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH, 2010, 44 (04): : 37 - 54
  • [9] Partial Least Squares learning regression for Backpropagation network
    Hsiao, TC
    Lin, CW
    Chiang, HHK
    PROCEEDINGS OF THE 22ND ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-4, 2000, 22 : 975 - 977
  • [10] Equivalence of backpropagation and contrastive Hebbian learning in a layered network
    Xie, XH
    Seung, HS
    NEURAL COMPUTATION, 2003, 15 (02) : 441 - 454
12345