CALCULATING THE UPPER AND LOWER BOUNDS ON THE CAPACITY OF 2 MODIFIED HEBBIAN TRAINED HOPFIELD NETWORKS

被引:0
作者
HOUSELANDER, P
TAYLOR, JT
机构
[1] Department of Electronic and Electrical Engineering, University College, London, WC17JE, Torrington Place
关键词
Associative memories; Hopfield networks; Neural networks;
D O I
10.1049/el:19900815
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A simple mathematical technique to evaluate the performance in terms of capacity of two versions of the Hopfield network is demonstrated. The calculated performance is compared with values derived from simulation. An important feature of the analysis is that it can be easily extended to other Hebbian trained associative memories. © 1990, The Institution of Electrical Engineers. All rights reserved.
引用
收藏
页码:1266 / 1267
页数:2
相关论文
共 6 条
  • [1] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES
    HOPFIELD, JJ
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08): : 2554 - 2558
  • [2] HOUSELANDER P, 1990, IEEE ISCAS 90
  • [3] COMPARING PERFORMANCE OF HEBBIAN-TRAINED AND DELTA-TRAINED HOPFIELD NETWORKS
    HOUSELANDER, PK
    TAYLOR, JT
    [J]. ELECTRONICS LETTERS, 1990, 26 (02) : 85 - 87
  • [4] MCELIECE R, 1987, IEEE T, V33
  • [5] OH S, 1988, OPT LETT, V23, P74
  • [6] Weatherburn, 1946, 1 COURSE MATH STAT