Disappearance of spurious states in analog associative memories

被引：9
|
作者：
Roudi, Y [1 ]
Treves, A [1 ]
机构：
[1] SISSA, Programme Neurosci, I-34014 Trieste, Italy
来源：
PHYSICAL REVIEW E | 2003年 / 67卷 / 04期
关键词：
D O I：
10.1103/PhysRevE.67.041906
中图分类号：
O35 [流体力学]; O53 [等离子体物理学];
学科分类号：
070204 ; 080103 ; 080704 ;
摘要：
We show that symmetric n-mixture states, when they exist, are almost never stable in autoassociative networks with threshold-linear units. Only with a binary coding scheme, we could find a limited region of the parameter space in which either 2-mixture or 3-mixture states are stable attractors of the dynamics.
引用
收藏
页码：419061 / 419065
页数：5
相关论文
共 50 条
  • [31] MULTIPLICATIVE CONTEXTS IN ASSOCIATIVE MEMORIES
    MIZRAJI, E
    POMI, A
    ALVAREZ, F
    BIOSYSTEMS, 1994, 32 (03) : 145 - 161
  • [32] Maximum Likelihood Associative Memories
    Gripon, Vincent
    Rabbat, Michael
    2013 IEEE INFORMATION THEORY WORKSHOP (ITW), 2013,
  • [33] NONLINEAR HOLOGRAPHIC ASSOCIATIVE MEMORIES
    OWECHKO, Y
    IEEE JOURNAL OF QUANTUM ELECTRONICS, 1989, 25 (03) : 619 - 634
  • [34] INFORMATION CAPACITY OF ASSOCIATIVE MEMORIES
    KUH, A
    DICKINSON, BW
    IEEE TRANSACTIONS ON INFORMATION THEORY, 1989, 35 (01) : 59 - 68
  • [35] ASSOCIATIVE-PROCESSORS AND MEMORIES
    GROSSPIETSCH, KE
    IEEE MICRO, 1992, 12 (03) : 10 - 11
  • [36] Implementation of associative memories by software
    Gall, R.
    Nagl, M.
    IT - Information Technology, 1981, 23 (1-6): : 61 - 71
  • [37] Semantic graphs and associative memories
    Pomi, A
    Mizraji, E
    PHYSICAL REVIEW E, 2004, 70 (06)
  • [38] Coupled Neural Associative Memories
    Karbasi, Amin
    Salavati, Amir Hesam
    Shokrollahi, Amin
    2013 IEEE INFORMATION THEORY WORKSHOP (ITW), 2013,
  • [39] Spherical Separability: Associative Memories
    Garimella, Ramamurthy
    Tata, Jagannadha Swamy
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2021, 2024, 13102 : 271 - 279
  • [40] ON SPARSELY CODED ASSOCIATIVE MEMORIES
    BUHMANN, J
    DIVKO, R
    SCHULTEN, K
    NEURAL NETWORKS FROM MODELS TO APPLICATIONS, 1989, : 360 - 371
12345