Automation, Control and Intelligent Systems

| Peer-Reviewed |

Multiplex Communication with Synchronous Shift and Weight Learning in 2D Mesh Neural Network

Received: 07 August 2015    Accepted: 21 August 2015    Published: 09 September 2015
Views:       Downloads:

Share This Article

Abstract

We have previously proposed a multiplex communication system in a neural network. However, this system is designed to force the network to communicate in a multiplexed manner, in which “codes” or “temporal sequences” are inevitably induced. This means that the network has a main loop and coding/decoding circuits, which are somewhat artificial. In this paper, we show that it is also possible to communicate without these artificial guidance aids by multiplexing in a 2D mesh-type neural network, where learning procedures are used to find paths from an originating neuron to a destination neuron. We also provide statistics from these neural networks to show that random sequences occur more frequently than non-random sequences.

DOI 10.11648/j.acis.20150305.11
Published in Automation, Control and Intelligent Systems (Volume 3, Issue 5, October 2015)
Page(s) 63-70
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Brain Information Processing, Neural Circuit, Pseudo-Random Sequence, M-Sequence, Multiplex Communication

References
[1] Yuko Matsumoto-Mizuno, Kozo Okazaki, Amami Kato, Toshiki Yoshimine, Yoshinobu Sato, Shinichi Tamura, and Toru Hayakawa: ``Visualization of epileptogenic phenomena using crosscorrelation analysis: Localization of epileptic foci and propagation of epileptiform discharges,'' IEEE Transactions on Biomedical Engineering, Vol. 46, No. 3, pp. 271–279, 1999.
[2] Yuko Mizuno-Matsumoto, Masatsugu Ishijima, Kazuhiro Shinosaki, Takashi Nishikawa, Satoshi Ukai, Yoshitaka Ikejiri, Yoshitsugu Nakagawa, Ryouhei Ishii, Hiromasa Tokunaga, Shinichi Tamura, Susumu Date, Tsuyoshi Inouye, Shinji Shimojo, Masatoshi Takeda: ``Transient Global Amnesia (TGA) in an MEG Study,'' Brain Topography, Vol.13, No.4, pp.269-274, 2001.
[3] Peter C Hansen, Morten L Kringelbach, Riitta Salmelin, MEG: An Introduction to Methods, Oxford University Press Inc. New York, 2010.
[4] Shinichi Tamura, Yoshi Nishitani, Takuya Kamimura, Yasushi Yagi, Chie Hosokawa, Tomomitsu Miyoshi, Hajime Sawai, Yuko Mizuno-Matsumoto, Yen-Wei Chen. “Multiplexed Spatiotemporal Communication Model in Artificial Neural Networks,” Automation, Control and Intelligent Systems. Vol. 1, No. 6, 2013, pp. 121-130. doi: 10.11648/j.acis.20130106.11.
[5] S. W. Golomb, G. Gong, Signal Design for Good Correlation: For Wireless Communication and Rader, Cambridge University Press. 2005.
[6] Yoshi Nishitani, Chie Hosokawa, Yuko Mizuno-Matsumoto, Tomomitsu Miyoshi, Hajime Sawai and Shinichi Tamura, ``Detection of M-sequences from spike sequence in neuronal networks,'' Computational Intelligence and Neuroscience - Special issue on Computational Intelligence in Biomedical Science and Engineering Volume 2012, 2012.
[7] Shinichi Tamura, Yoshi Nishitani, Chie Hosokawa, Yuko Mizuno-Matsumoto, Takuya Kamimura, Yen-Wei Chen, Tomomitsu Miyoshi, Hajime Sawai. “M-sequence family from cultured neural circuits,'' 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM 2012), Oct. 23-25, 2012.
[8] Daniel L. Schacter, Daniel T. Gilbert, Daniel M. Wegner, Psychology (2nd ed.), Worth Publishers, New York, 2011.
[9] Christophe Lecerf, ”The double loop as a model of a learning neural system,'' Proceedings World Multiconference on Systemics, Cybernetics and Informatics, Vol.1, pp. 587-594, 1998.
[10] Y. Choe, "Analogical cascade: a theory on the role of the thalamo-cortical loop in brain function," Neurocomputing 52-54, pp.713-719, 2003.
[11] Takuya Kamimura, Yoshi Nishitani, Yen-Wei Chen, Yasushi Yagi, and Shinichi Tamura, “Copy of neural loop circuits for memory and communication,” Journal of Communications and Information Sciences, Vol.4, No.1, pp.46-56, Jan 2014.
[12] Wulfram Gerstner and Werner Kistler, Spiking Neuron Models. Single Neurons, Populations, Plasticity, Cambridge University Press, 2002.
[13] Daniel Delling, Peter Sanders, Dominik Schultes, Dorothea Wagner, “Engineering Route Planning Algorithms,” in Jürgen Lerner, Dorothea Wagner, Katharina A. Zweig (eds.), Algorithmics of Large and Complex Networks, Design, Analysis, and Simulation, 2009.
[14] Paulsen, O.; Sejnowski, T. J. (2000). "Natural patterns of activity and long-term synaptic plasticity". Current Opinion in Neurobiology, 10 (2): 172–179. doi:10.1016/S0959-4388(00)00076-3.
[15] Steven Yantis, Sensation and Perception, Worth Publishers, New York, 2014.
Author Information
  • NBL Technovator Co., Ltd. Shindachimakino, Sennan, Japan

  • ISIR, Osaka University, Mihogaoka, Ibaraki City, Osaka, Japan

  • NBL Technovator Co., Ltd. Shindachimakino, Sennan, Japan

  • Ritsumeikan University, Nojihigashi, Kusatsu-shi, Shiga, Japan

Cite This Article
  • APA Style

    Takuya Kamimura, Yasushi Yagi, Shinichi Tamura, Yen-Wei Chen. (2015). Multiplex Communication with Synchronous Shift and Weight Learning in 2D Mesh Neural Network. Automation, Control and Intelligent Systems, 3(5), 63-70. https://doi.org/10.11648/j.acis.20150305.11

    Copy | Download

    ACS Style

    Takuya Kamimura; Yasushi Yagi; Shinichi Tamura; Yen-Wei Chen. Multiplex Communication with Synchronous Shift and Weight Learning in 2D Mesh Neural Network. Autom. Control Intell. Syst. 2015, 3(5), 63-70. doi: 10.11648/j.acis.20150305.11

    Copy | Download

    AMA Style

    Takuya Kamimura, Yasushi Yagi, Shinichi Tamura, Yen-Wei Chen. Multiplex Communication with Synchronous Shift and Weight Learning in 2D Mesh Neural Network. Autom Control Intell Syst. 2015;3(5):63-70. doi: 10.11648/j.acis.20150305.11

    Copy | Download

  • @article{10.11648/j.acis.20150305.11,
      author = {Takuya Kamimura and Yasushi Yagi and Shinichi Tamura and Yen-Wei Chen},
      title = {Multiplex Communication with Synchronous Shift and Weight Learning in 2D Mesh Neural Network},
      journal = {Automation, Control and Intelligent Systems},
      volume = {3},
      number = {5},
      pages = {63-70},
      doi = {10.11648/j.acis.20150305.11},
      url = {https://doi.org/10.11648/j.acis.20150305.11},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.acis.20150305.11},
      abstract = {We have previously proposed a multiplex communication system in a neural network. However, this system is designed to force the network to communicate in a multiplexed manner, in which “codes” or “temporal sequences” are inevitably induced. This means that the network has a main loop and coding/decoding circuits, which are somewhat artificial. In this paper, we show that it is also possible to communicate without these artificial guidance aids by multiplexing in a 2D mesh-type neural network, where learning procedures are used to find paths from an originating neuron to a destination neuron. We also provide statistics from these neural networks to show that random sequences occur more frequently than non-random sequences.},
     year = {2015}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Multiplex Communication with Synchronous Shift and Weight Learning in 2D Mesh Neural Network
    AU  - Takuya Kamimura
    AU  - Yasushi Yagi
    AU  - Shinichi Tamura
    AU  - Yen-Wei Chen
    Y1  - 2015/09/09
    PY  - 2015
    N1  - https://doi.org/10.11648/j.acis.20150305.11
    DO  - 10.11648/j.acis.20150305.11
    T2  - Automation, Control and Intelligent Systems
    JF  - Automation, Control and Intelligent Systems
    JO  - Automation, Control and Intelligent Systems
    SP  - 63
    EP  - 70
    PB  - Science Publishing Group
    SN  - 2328-5591
    UR  - https://doi.org/10.11648/j.acis.20150305.11
    AB  - We have previously proposed a multiplex communication system in a neural network. However, this system is designed to force the network to communicate in a multiplexed manner, in which “codes” or “temporal sequences” are inevitably induced. This means that the network has a main loop and coding/decoding circuits, which are somewhat artificial. In this paper, we show that it is also possible to communicate without these artificial guidance aids by multiplexing in a 2D mesh-type neural network, where learning procedures are used to find paths from an originating neuron to a destination neuron. We also provide statistics from these neural networks to show that random sequences occur more frequently than non-random sequences.
    VL  - 3
    IS  - 5
    ER  - 

    Copy | Download

  • Sections