single-jc.php

JACIII Vol.27 No.1 pp. 44-53
doi: 10.20965/jaciii.2023.p0044
(2023)

Research Paper:

Dynamic Pattern Recognition Model Based on Neural Network Response to Signal Fluctuation

Hirotaka Doho*, Haruhiko Nishimura**, and Sou Nobukawa***

*Faculty of Education, Kochi University
2-5-1 Akebono-cho, Kochi 780-8520, Japan

**Graduate School of Applied Informatics, University of Hyogo
7-1-28 Minatojima-Minami-cho, Chuo-ku, Kobe, Hyogo 650-0047, Japan

***Department of Computer Science, Chiba Institute of Technology
2-17-1 Tsudanuma, Narashino, Chiba 275-0016, Japan

Received:
July 21, 2020
Accepted:
August 10, 2022
Published:
January 20, 2023
Keywords:
neural network, signal fluctuation, pattern recognition, associative memory, input/output correlation
Abstract

We have proposed a model of dynamic retrieval in associative memory based on temporal input/output correlations under a stimulus-response open scheme of neural networks. This mechanism is different from that of the conventional stationary Hopfield model in which the input signal is used only as information for the initial state of the network. Building upon the fundamental properties of the proposed model, in this paper, we newly evaluate the dependence of identification performance on the signal fluctuation level and on the number of stored patterns by introducing an accuracy rate for known (stored) and unknown (non-stored) patterns, based on the network correlation to the input signal with fluctuation. The results indicate that the dynamic scheme of network response to a fluctuating signal leads to increased efficacy and usefulness.

Cite this article as:
H. Doho, H. Nishimura, and S. Nobukawa, “Dynamic Pattern Recognition Model Based on Neural Network Response to Signal Fluctuation,” J. Adv. Comput. Intell. Intell. Inform., Vol.27 No.1, pp. 44-53, 2023.
Data files:
References
  1. [1] J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. of the National Academy of Sciences of the United States of America, Vol.79, No.8, pp. 2554-2558, 1982.
  2. [2] J. J. Hopfield, “Neurons with graded response have collective computational properties like those of two-state neurons,” Proc. of the National Academy of Sciences of the United States of America, Vol.81, pp. 3088-3092, 1984.
  3. [3] S. S. Haykin, “Neural Networks: A Complehensive Foundation,” Macmillan USA, 1994.
  4. [4] B. Müller and J. Reinhardt, “Neural Networks: An Introduction,” Springer-Verlag, Berlin Heidelberg, 1995.
  5. [5] M. K. Müezzinoglu, C. Güzeliş, and J. M. Zurada, “An energy function-based design method for discrete Hopfield associative memory with attractive fixed points,” IEEE Trans. on Neural Networks, Vol.16, No.2, pp. 370-378, 2005.
  6. [6] G. Pajares, “A Hopfield Neural Network for Image Change Detection,” IEEE Trans. on Neural Networks, Vol.17, No.5, pp. 1250-1264, 2006.
  7. [7] R. Kruse, S. Mostaghim, C. Borgelt, C. Braune, and M. Steinbrecher, “Hopfield networks” in “Computational Intelligence,” Springer, London, 2016.
  8. [8] K. Aihara, T. Takabe, and M. Toyoda, “Chaotic neural networks,” Phys. Lett. A, Vol.144, No.6, pp. 333-340, 1990.
  9. [9] M. Adachi and K. Aihara, “Associative dynamics in a chaotic neural network,” Neural Network, Vol.10, No.1, pp. 83-98, 1997.
  10. [10] M. Riani and E. Simonotto, “Stochastic resonance in the perceptual interpretation of ambiguous figures: A neural network model,” Phys. Rev. Lett., Vol.72, No.19, pp. 3120-3123, 1994.
  11. [11] N. Katada and H. Nishimura, “Stochastic resonance in recurrent neural network with Hopfield-type memory,” Neural Process. Lett., Vol.30, pp. 145-154, 2009.
  12. [12] H. Nishimura, N. Katada, and Y. Fujita, “Dynamic learning and retrieving scheme based on chaotic neuron model,” E. R. Nakamura et al. (Eds.), “Complexity and Diversity,” pp. 64-66, Springer-Verlag, Tokyo, 1997.
  13. [13] H. Nishimura and N. Katada, “Dynamic learning characteristics of chaotic neural networks with stimulus-response scheme,” Trans. of the Institute of Systems, Control and information Engineers, Vol.10, No.10, pp. 518-527, 1997 (in Japanese).
  14. [14] H. Nishimura, N. Katada, and K. Aihara, “Coherent response in a chaotic neural network,” Neural Process. Lett., Vol.12, pp. 49-58, 2000.
  15. [15] H. Nishimura, H. Doho, and N. Katada, “Signal recognition by input-output correlation in associative neural networks,” Electronics and Communications in Japan (Part III: Fundamental Electronic Science), Vol.86, Issue 5, pp. 54-64, 2003.
  16. [16] H. Doho, H. Nishimura, and N. Katada, “Dynamic pattern recognition model based on the characteristics of neural network response to signal fluctuation,” Proc. of 18th Fuzzy, Artificial Intelligence, Neural Networks and Computational Intelligence, pp. 491-496, 2008 (in Japanese).
  17. [17] C. M. Marcus and R. M. Westervelt, “Dynamics of iterated-map neural networks,” Phys. Rev. A, Vol.40, No.1, pp. 501-504, 1989.
  18. [18] P. Koiran, “Dynamics of discrete time continuous state Hopfield networks,” Neural Computation, Vol.6, No.3, pp. 459-468, 1994.
  19. [19] S. Diederich and M. Opper, “Learning of correlated patterns in spin-grass networks by local learning rules,” Phys. Rev. Lett., Vol.58, No.9, pp. 949-952, 1987.
  20. [20] D. O. Hebb, “The Organization of Behavior,” Wiley, New York, 1949.
  21. [21] N. Hiratani, J. Teramae, and T. Fukai, “Associative memory model with long-tail-distributed Hebbian synaptic connections,” Front Comput. Neuroscience, Vol.6, 2013. https://doi.org/10.3389/fncom.2012.00102
  22. [22] W. Gerstner, W. M. Kistler, R. Naud, and L. Paninski, “Memory Networks with Spiking Neurons, Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition,” Cambridge University Press, 2014.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Dec. 02, 2024