Multi-pattern real-valued spectral associative memories

被引:0
|
作者
Spencer, RG [1 ]
机构
[1] Texas A&M Univ, Dept Elect Engn, College Stn, TX 77843 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A multi-pattern encoding and decoding scheme is presented that extends the family of spectral associative memories (SAMs) to include gray-level, or analog patterns. SAMs are frequency-domain formulations of associative memory that combine the extrinsic redundancy of neural networks with the in-phase, quadrature, and complex modulation schemes of communications. Considerable coding gain occurs at the level of modulation and these networks may be regarded as multi-channel, multi-carrier generalizations of amplitude modulation. Unlike multi-pattern bipolar SAMs, which are exclusively content-addressable, real-valued SAMs also have an address-addressable mode in which the recall of a particular memory may be forced. Band structures and anti-aliasing constraints are presented along with a probabilistic formulation in which virtual entanglement is a natural feature. Simulations are presented that demonstrate dual-memory recall for 6x6 gray-level patterns.
引用
收藏
页码:1180 / 1185
页数:6
相关论文
共 50 条
  • [1] New associative memories to recall real-valued patterns
    Sossa, H
    Barrón, R
    Váquez, RA
    [J]. PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS AND APPLICATIONS, 2004, 3287 : 195 - 202
  • [2] Real-valued pattern recall by associative memory
    Sossa, H
    Barrón, R
    Oropeza, JL
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE - IBERAMIA 2004, 2004, 3315 : 646 - 655
  • [3] Associative memory based real-valued pattern recall
    Sossa, H
    Barrón, R
    Oropeza, JL
    Cortés, H
    [J]. PROCEEDINGS OF THE FIFTH MEXICAN INTERNATIONAL CONFERENCE IN COMPUTER SCIENCE (ENC 2004), 2004, : 206 - 212
  • [4] Real-valued pattern classification based on extended associative memory
    Sossa, H
    Barrón, R
    Vazquez, RA
    [J]. PROCEEDINGS OF THE FIFTH MEXICAN INTERNATIONAL CONFERENCE IN COMPUTER SCIENCE (ENC 2004), 2004, : 213 - 219
  • [5] Unbounded Capacity Associative Memory for Real-valued Pattern Storage and Recall
    Salem, Fathi M.
    [J]. 2021 IEEE INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2021, : 1066 - 1069
  • [6] Recovery of real-valued sparse models in the multi-dimensional spectral domain
    Callejas-Ramos, Alvaro
    Sanchez-Fernandez, Matilde
    Tulino, Antonia
    Murillo-Fuentes, Juan Jose
    [J]. 2023 IEEE 9TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL ADVANCES IN MULTI-SENSOR ADAPTIVE PROCESSING, CAMSAP, 2023, : 111 - 115
  • [7] Retrieval Performance of Hopfield Associative Memory with Complex-Valued and Real-Valued Neurons
    Minemoto, Toshifumi
    Isokawa, Teijiro
    Matsui, Nobuyuki
    Kobayashi, Masaki
    Nishimura, Haruhiko
    [J]. 2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 4133 - 4138
  • [8] Chaotic complex-valued bidirectional associative memory with a real-valued context part
    Furusawa, Shogo
    Kobayashi, Masaki
    [J]. IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2013, 4 (03): : 299 - 312
  • [9] A coding procedure for real-valued patterns using bidirectional associative memory
    Abedin, MJ
    [J]. ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 1998, 23 (1B): : 67 - 82
  • [10] A REAL-VALUED SPECTRAL DECOMPOSITION OF THE UNDAMPED GYROSCOPIC SYSTEM WITH APPLICATIONS
    Jia, Zhigang
    Wei, Musheng
    [J]. SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2011, 32 (02) : 584 - 604