On the design of BSB neural associative memories using semidefinite programming

被引：8
|
作者：
Park, J [1 ]
Cho, H
Park, D
机构：
[1] Korea Univ, Dept Control & Instrumentat Engn, Chungnam 339800, South Korea
[2] Korea Univ, Dept Comp Sci, Chungnam 339800, South Korea
来源：
NEURAL COMPUTATION | 1999年 / 11卷 / 08期
关键词：
D O I：
10.1162/089976699300016052
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This article is concerned with the reliable search for optimally performing BSB (brain state in a box) neural associative memories given a set of prototype patterns to be stored as stable equilibrium points. By converting and/or modifying the nonlinear constraints of a known formulation for the synthesis of BSB-based associative memories into linear matrix inequalities, we recast the synthesis into semidefinite programming problems and solve them by recently developed interior point methods. The validity of this approach is illustrated by a design example.
引用
收藏
页码：1985 / 1994
页数：10
相关论文
共 50 条
  • [41] On the associative memories in cellular neural networks
    Kawabata, H
    Nanba, M
    Zhang, Z
    SMC '97 CONFERENCE PROCEEDINGS - 1997 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: CONFERENCE THEME: COMPUTATIONAL CYBERNETICS AND SIMULATION, 1997, : 929 - 933
  • [42] Clone-Based Encoded Neural Networks to Design Efficient Associative Memories
    Wouafo, Hugues
    Chavet, Cyrille
    Coussy, Philippe
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (10) : 3186 - 3199
  • [43] The BSB neural network in the convex body spanned by the prototype patterns for associative memory
    Tao, Q
    Cao, J
    Liu, X
    APPLIED MATHEMATICS AND COMPUTATION, 2002, 132 (2-3) : 575 - 587
  • [44] Evolutionary computation applied to the automatic design of artificial neural networks and associative memories
    Sossa, Humberto
    Garro, Beatriz A.
    Villegas, Juan
    Olague, Gustavo
    Avilés, Carlos
    Advances in Intelligent Systems and Computing, 2013, 175 ADVANCES : 285 - 297
  • [45] Evolutionary Computation Applied to the Automatic Design of Artificial Neural Networks and Associative Memories
    Sossa, Humberto
    Garro, Beatriz A.
    Villegas, Juan
    Olague, Gustavo
    Aviles, Carlos
    EVOLVE - A BRIDGE BETWEEN PROBABILITY, SET ORIENTED NUMERICS, AND EVOLUTIONARY COMPUTATION II, 2013, 175 : 285 - +
  • [46] Lyapunov diagonally stable matrices to design cellular neural networks for associative memories
    Grassi, G
    CNNA 98 - 1998 FIFTH IEEE INTERNATIONAL WORKSHOP ON CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS - PROCEEDINGS, 1998, : 410 - 415
  • [47] Optimal and robust design of brain-state-in-a-box neural associative memories
    Park, Yonmook
    NEURAL NETWORKS, 2010, 23 (02) : 210 - 218
  • [48] CONSTRUCTING ASSOCIATIVE MEMORIES USING HIGH-ORDER NEURAL NETWORKS
    TSENG, YH
    WU, JL
    ELECTRONICS LETTERS, 1992, 28 (12) : 1122 - 1124
  • [49] Associative memories in cellular neural networks using a singular value decomposition
    Kawabata, H
    Zhang, Z
    Kanagawa, A
    Takahashi, H
    Kuwaki, H
    ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 1997, 80 (01): : 59 - 68
  • [50] Overlapping decompositions in the design of associative memories
    Akar, M
    Sezer, ME
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1199 - 1204
12345