The Sparse Blume - Emery - Griffiths Model of Associative Memories

被引：0
|
作者：
Heusel, J. [1 ]
Loewe, M. [1 ]
机构：
[1] Univ Munster, Fachbereich Math & Informat, Einsteinstr 62, D-48149 Munster, Germany
来源：
MARKOV PROCESSES AND RELATED FIELDS | 2018年 / 24卷 / 05期
关键词：
Associative memory; storage capacity; sparse data; artificial intelligence; machine learning; exponential inequalities; negative association; STORAGE CAPACITY; NEURAL-NETWORKS; HOPFIELD MODEL; INFORMATION; RETRIEVAL; BOUNDS;
D O I：
暂无
中图分类号：
O21 [概率论与数理统计]; C8 [统计学];
学科分类号：
020208 ; 070103 ; 0714 ;
摘要：
We analyze the Blume -Emery- Griffiths (BEG) associative memory with sparse patterns and at zero temperature. We give bounds on its storage capacity provided that we want the stored patterns to be fixed points of the retrieval dynamics. We compare our results to that of other models of sparse neural networks and show that the BEG model has a superior performance compared to them.
引用
收藏
页码：779 / 810
页数：32
相关论文
共 50 条
  • [1] A Comparative Study of Sparse Associative Memories
    Gripon, Vincent
    Heusel, Judith
    Loewe, Matthias
    Vermet, Franck
    JOURNAL OF STATISTICAL PHYSICS, 2016, 164 (01) : 105 - 129
  • [2] A Comparative Study of Sparse Associative Memories
    Vincent Gripon
    Judith Heusel
    Matthias Löwe
    Franck Vermet
    Journal of Statistical Physics, 2016, 164 : 105 - 129
  • [3] Neural associative memories and sparse coding
    Palm, Guenther
    NEURAL NETWORKS, 2013, 37 : 163 - 169
  • [4] Associative Memories to Accelerate Approximate Nearest Neighbor Search
    Gripon, Vincent
    Loewe, Matthias
    Vermet, Franck
    APPLIED SCIENCES-BASEL, 2018, 8 (09):
  • [5] On the capacity of an associative memory model based on neural cliques
    Heusel, Judith
    Loewe, Matthias
    Vermet, Franck
    STATISTICS & PROBABILITY LETTERS, 2015, 106 : 256 - 261
  • [6] Capacity of an associative memory model on random graph architectures
    Loewe, Matthias
    Vermet, Franck
    BERNOULLI, 2015, 21 (03) : 1884 - 1910
  • [7] Transfer Learning with Sparse Associative Memories
    Jodelet, Quentin
    Gripon, Vincent
    Hagiwara, Masafumi
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: THEORETICAL NEURAL COMPUTATION, PT I, 2019, 11727 : 497 - 512
  • [8] NEURAL ASSOCIATIVE MEMORIES WITH MINIMUM CONNECTIVITY
    CAIANIELLO, ER
    DEBENEDICTIS, A
    PETROSINO, A
    TAGLIAFERRI, R
    NEURAL NETWORKS, 1992, 5 (03) : 433 - 439
  • [9] Sparse Binary Matrices as Efficient Associative Memories
    Gripon, Vincent
    Skachek, Vitaly
    Rabbat, Michael
    2014 52ND ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2014, : 499 - 504
  • [10] On a Model of Associative Memory with Huge Storage Capacity
    Demircigil, Mete
    Heusel, Judith
    Loewe, Matthias
    Upgang, Sven
    Vermet, Franck
    JOURNAL OF STATISTICAL PHYSICS, 2017, 168 (02) : 288 - 299
12345