Some Aspects of Associative Memory Construction Based on a Hopfield Network

被引：0
|
作者：
Yu. L. Karpov
L. E. Karpov
Yu. G. Smetanin
机构：
[1] Luxoft Professional LLC,
[2] Ivannikov Institute for System Programming,undefined
[3] Russian Academy of Sciences,undefined
[4] Moscow State University,undefined
[5] Federal Research Center Computer Science and Control,undefined
[6] Russian Academy of Sciences,undefined
[7] Moscow Institute of Physics and Technology,undefined
来源：
Programming and Computer Software | 2020年 / 46卷
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
An implementation of associative memory based on a Hopfield network is described. In the proposed approach, memory addresses are regarded as training vectors of the artificial neural network. The efficiency of memory search is directly associated with solving the overfitting problem. A method for dividing the training and input network vectors into parts, the processing of which requires a smaller number of neurons, is proposed. Results of a series of experiments conducted on Hopfield network models with different numbers of neurons trained with different numbers of vectors and operated under different noise conditions are presented.
引用
收藏
页码：305 / 311
页数：6
相关论文
共 50 条
  • [1] Some Aspects of Associative Memory Construction Based on a Hopfield Network
    Karpov, Yu. L.
    Karpov, L. E.
    Smetanin, Yu. G.
    PROGRAMMING AND COMPUTER SOFTWARE, 2020, 46 (05) : 305 - 311
  • [2] Associative memory in quaternionic hopfield neural network
    Isokawa, Teijiro
    Nishimura, Haruhiko
    Kamiura, Naotake
    Matsui, Nobuyuki
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2008, 18 (02) : 135 - 145
  • [3] Five variations of Hopfield associative memory network
    Schultz, Abraham
    Journal of artificial neural networks, 1995, 2 (03): : 285 - 294
  • [4] Hopfield network as associative memory with multiple reference points
    López-Rodríguez, D
    Mérida-Casermeiro, E
    Ortiz-de-Lazcano-Lobato, JM
    ENFORMATIKA, VOL 7: IEC 2005 PROCEEDINGS, 2005, : 62 - 67
  • [5] Hopfield Network as Associative Memory with Multiple Reference Points
    Lopez-Rodriguez, Domingo
    Merida-Casermeiro, Enrique
    Ortiz-de-Lazcano-Lobato, Juan M.
    PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 7, 2005, 7 : 62 - 67
  • [6] VLSI IMPLEMENTATION OF AN ASSOCIATIVE CONTENT ADDRESSABLE MEMORY BASED ON HOPFIELD NETWORK MODEL
    Ionescu, Laurentiu Mihai
    Mazare, Alin Gheorghita
    Serban, Gheorghe
    2010 INTERNATIONAL SEMICONDUCTOR CONFERENCE (CAS), VOLS 1 AND 2, 2010, : 499 - 502
  • [7] Associative memory framework for speech recognition: Adaptation of Hopfield network
    Vaishnavi, Y.
    Shreyas, R.
    Suhas, S.
    Surya, U. N.
    Ladwani, Vandana M.
    Ramasubramanian, V.
    2016 IEEE ANNUAL INDIA CONFERENCE (INDICON), 2016,
  • [8] NEURAL NETWORK MODELING OF ASSOCIATIVE MEMORY - BEYOND THE HOPFIELD MODEL
    DASGUPTA, C
    PHYSICA A, 1992, 186 (1-2): : 49 - 60
  • [9] The Hopfield associative memory network:: Improving performance with the kernel "trick"
    García, C
    Moreno, JA
    ADVANCES IN ARTIFICIAL INTELLIGENCE - IBERAMIA 2004, 2004, 3315 : 871 - 880
  • [10] Associative memory realized by a reconfigurable memristive Hopfield neural network
    Hu, S. G.
    Liu, Y.
    Liu, Z.
    Chen, T. P.
    Wang, J. J.
    Yu, Q.
    Deng, L. J.
    Yin, Y.
    Hosaka, Sumio
    NATURE COMMUNICATIONS, 2015, 6
12345