| Peer-Reviewed

Each Role of Short-term and Long-term Memory in Neural Networks

Received: 20 February 2020     Accepted: 10 March 2020     Published: 24 March 2020
Views:       Downloads:
Abstract

Based on known functions of neuroscience the neural network that performs serial parallel conversion and its inverse transformation is presented. By hierarchy connecting the neural networks, the upper neural network that can process general time sequence data is constructed. The activity of the upper neural networks changes in response to the context structure inherent in the time series data and have both function of accepting and generating of general time series data. Eating behavior in animals in the early stages of evolution is also processing time series data, and it is possible to predict behavior although be limited short term by learning the contextual structure inherent in time series data. This function is the behavior of so-called short-term memory. Transition of the activation portion in this type of operation is illustrated. Although status of nervous system of the animal change according to the recognition by sensory organ and to the manipulation of the object by muscle in the vicinity of the animal itself, the evolved animals have in addition another nervous system so-called long-term memory or episodic memory being involved experience and prediction. The nervous system of long-term memory behaves freely but keeping consistency of the change in the environment. By the workings of long-term memory, lot of information are exchanged between fellows, and lot of time series data are conserved by characters in human society. In this paper, the model of the transfer of data between different nervous systems is shown using the concept of category theory.

Published in American Journal of Neural Networks and Applications (Volume 6, Issue 1)
DOI 10.11648/j.ajnna.20200601.12
Page(s) 10-15
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), 2020. Published by Science Publishing Group

Keywords

Short-term Memory, Long-term Memory, Serial Parallel Conversion, Parallel Serial Conversion, Mirror Neuron, Prediction, Category Theory

References
[1] S. Yanagawa, “Neural Network That Learns Sequential Processing and Predicts by the Context.” In The 28th Annual Conference of the Japanese Neural Network Society (JNNS2018).
[2] S. Yanagawa “From Bacteria, a Consideration of the Evolution of Neural Network” Journal of Mechanics Engineering and Automation 1 (2019) p. 17-23.
[3] A. Damasio The Strange Order of Things Pantheon Books, New York, 2018 p. 62.
[4] T M. Iacoboni, “Mirroring People.” Picador 33. 2008, Chapter 4, p 106.
[5] T. Leinster “Basic Category Theory” Cambridge University Press 2017 p. 10.
[6] D. C. Dennet, “From Bacteria to Bach and Back: The Evolution of Minds.” In Penguin Books, 2018.
[7] S. Yanagawa “A neural network that processes time series data in which element data is linked to symbols Third International Workshop on Symbolic-Neural Learning (SNL-2019) Poster presentation.
[8] S. Yanagawa. 2017, “Learning Machine That Uses Context Structure to Search Policy.” https://jsai.ixsq.nii.ac.jp/.SIG-AGI-007-07.
[9] S. Dehaene, Consciousness and Brain Penguin Books, 2014.
[10] W. J. Freeman “How Brains Make up Their Minds” Weidenfeld & Nicolson Ltd. 1999.
[11] Hoon Keng Poon, Wun-She Yap, Yee-Kai Tee, Wai-Kong Lee, Bok-Min Goi “Hierarchical gated recurrent neural network with adversarial and virtual adversarial training on text classification”, Neural Networks 119 (2019) 299-312.
[12] L. Andrew Coward, Ron Sun, “Hierarchical approaches to understanding consciousness”, Neural Networks 20 (2007) 947-954.
[13] Qianli Ma, Wanqing Zhuang, Lifeng Shen, Garrison W. Cottrell, “Time series classification with Echo Memory Networks”, Neural Networks 117 (2019) 225-239.
[14] Paolo Arena, Marco Cali, Luca Patane, Agnese Portera, Roland StraussSC, “Modelling the insect Mushroom Bodies: Application to Sequence learning”, Neural Networks 67 (2015) 37-53.
[15] Michael j. Healy, Thomas P. Caudill, “Episodic memory: A hierarchy of spatiotemporal concepts”, Neural Networks 120 (2019) 40-57
[16] Kenji Doyaa & Tadahiro Taniguchi, “Toward Evolutionary and Developmental Intelligence”, Current Opinion in Behavioral Sciences Volume 29, October 2019, Pages 91-96.
[17] Ann Sizemore, Chad Giusti, Ari Kahn, Richard F. Betzel, Danielle S. Bassett “Cliques and Cavities in the Human Connectome”, Cornell University arxiv.org/abs/1608.03520, 2016.
[18] Hiroshi Yamakawa, “Attentional Reinforcement Learning in the Brain”, New Generation Computing, January 2020.
Cite This Article
  • APA Style

    Seisuke Yanagawa. (2020). Each Role of Short-term and Long-term Memory in Neural Networks. American Journal of Neural Networks and Applications, 6(1), 10-15. https://doi.org/10.11648/j.ajnna.20200601.12

    Copy | Download

    ACS Style

    Seisuke Yanagawa. Each Role of Short-term and Long-term Memory in Neural Networks. Am. J. Neural Netw. Appl. 2020, 6(1), 10-15. doi: 10.11648/j.ajnna.20200601.12

    Copy | Download

    AMA Style

    Seisuke Yanagawa. Each Role of Short-term and Long-term Memory in Neural Networks. Am J Neural Netw Appl. 2020;6(1):10-15. doi: 10.11648/j.ajnna.20200601.12

    Copy | Download

  • @article{10.11648/j.ajnna.20200601.12,
      author = {Seisuke Yanagawa},
      title = {Each Role of Short-term and Long-term Memory in Neural Networks},
      journal = {American Journal of Neural Networks and Applications},
      volume = {6},
      number = {1},
      pages = {10-15},
      doi = {10.11648/j.ajnna.20200601.12},
      url = {https://doi.org/10.11648/j.ajnna.20200601.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20200601.12},
      abstract = {Based on known functions of neuroscience the neural network that performs serial parallel conversion and its inverse transformation is presented. By hierarchy connecting the neural networks, the upper neural network that can process general time sequence data is constructed. The activity of the upper neural networks changes in response to the context structure inherent in the time series data and have both function of accepting and generating of general time series data. Eating behavior in animals in the early stages of evolution is also processing time series data, and it is possible to predict behavior although be limited short term by learning the contextual structure inherent in time series data. This function is the behavior of so-called short-term memory. Transition of the activation portion in this type of operation is illustrated. Although status of nervous system of the animal change according to the recognition by sensory organ and to the manipulation of the object by muscle in the vicinity of the animal itself, the evolved animals have in addition another nervous system so-called long-term memory or episodic memory being involved experience and prediction. The nervous system of long-term memory behaves freely but keeping consistency of the change in the environment. By the workings of long-term memory, lot of information are exchanged between fellows, and lot of time series data are conserved by characters in human society. In this paper, the model of the transfer of data between different nervous systems is shown using the concept of category theory.},
     year = {2020}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Each Role of Short-term and Long-term Memory in Neural Networks
    AU  - Seisuke Yanagawa
    Y1  - 2020/03/24
    PY  - 2020
    N1  - https://doi.org/10.11648/j.ajnna.20200601.12
    DO  - 10.11648/j.ajnna.20200601.12
    T2  - American Journal of Neural Networks and Applications
    JF  - American Journal of Neural Networks and Applications
    JO  - American Journal of Neural Networks and Applications
    SP  - 10
    EP  - 15
    PB  - Science Publishing Group
    SN  - 2469-7419
    UR  - https://doi.org/10.11648/j.ajnna.20200601.12
    AB  - Based on known functions of neuroscience the neural network that performs serial parallel conversion and its inverse transformation is presented. By hierarchy connecting the neural networks, the upper neural network that can process general time sequence data is constructed. The activity of the upper neural networks changes in response to the context structure inherent in the time series data and have both function of accepting and generating of general time series data. Eating behavior in animals in the early stages of evolution is also processing time series data, and it is possible to predict behavior although be limited short term by learning the contextual structure inherent in time series data. This function is the behavior of so-called short-term memory. Transition of the activation portion in this type of operation is illustrated. Although status of nervous system of the animal change according to the recognition by sensory organ and to the manipulation of the object by muscle in the vicinity of the animal itself, the evolved animals have in addition another nervous system so-called long-term memory or episodic memory being involved experience and prediction. The nervous system of long-term memory behaves freely but keeping consistency of the change in the environment. By the workings of long-term memory, lot of information are exchanged between fellows, and lot of time series data are conserved by characters in human society. In this paper, the model of the transfer of data between different nervous systems is shown using the concept of category theory.
    VL  - 6
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • OptID, Machida, Tokyo, Japan

  • Sections