Journal of Electrical and Electronic Engineering

| Peer-Reviewed |

A Schmitt Trigger Based Oscillatory Neural Network for Reservoir Computing

Received: 15 November 2019    Accepted: 02 December 2019    Published: 04 January 2020
Views:       Downloads:

Share This Article

Abstract

With the increase in communication bandwidth and frequency, the development level of communication technology is also constantly developing. The scale of the Internet of Things (IoT) has shifted from single point-to-point communication to mesh communication between sensors. However, the large sensors serving the infrastructure place a burden on real-time monitoring, data transmission, and even data analysis. The information processing method is experimentally demonstrated with a non-linear Schmitt trigger oscillator. A neuronally inspired concept called reservoir computing has been implemented. The synchronization frequency prediction tasks are utilized as benchmarks to reduce the computational load. The oscillator's oscillation frequency is affected by the sensor input, further affecting the storage pattern of the oscillatory neural network. This paper proposes a method of information processing by training and modulating the weights of the intrinsic electronic neural network to achieve the next step prediction. The effects on the frequency of a single oscillator in a coupled oscillatory neural network are studied under asynchronous and synchronization modes. Principle Component Analysis (PCA) is used to reduce the data dimension, and Support Vector Machine (SVM) is used to classify the synchronous and asynchronous data. We define that oscillator with stronger coupling weight (lower coupling resistance) as a leader oscillator. From the spice simulation, when OSC1 and OSC2 work as leader oscillator, the ONN almost always achieve synchronization; and the synchronization frequency is close to the average value of the leader oscillators. By training the emerging synchronous and asynchronous data, we can predict the synchronization status of an unknown dataset. Weight retrieval can be achieved by adjusting the slope and bias of the separation boundary.

DOI 10.11648/j.jeee.20200801.11
Published in Journal of Electrical and Electronic Engineering (Volume 8, Issue 1, February 2020)
Page(s) 1-9
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

Schmitt Trigger Oscillator, Reservoir Computing, Coupling Weight, Synchronization Frequency

References
[1] Y. Li, Q. Ma, M. R. Haider, and Y. Massoud,”Ultra-low-power high sensitivity spike detectors based on modified nonlinear energy operator,” 2013 IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, pp. 137-140, 2013.
[2] A. K. M., Arifuzzman, M. S., Islam, and M. R. Haider.”A Neuron Model-Based Ultralow Current Sensor System for Bioapplications.” Journal of Sensors, 2016.
[3] T., Zhang, M. R. Haider, Y. Massoud and J. Alexander.”An Oscillatory Neural Network Based Local Processing Unit for Pattern Recognition Applications.” Electronics, 8 (1), p. 64, 2019.
[4] Q. Ma, Y. Li, M. R. Haider and Y. Massoud,”A low-power neuromorphic bandpass filter for biosignal processing,” WAMICON 2013, Orlando, FL, 2013, pp. 1-3.
[5] Y. Li, Y. Massoud and M. R. Haider. Low-power high-sensitivity spike detectors for implantable VLSI neural recording microsystems. Analog Integrated Circuits and Signal Processing, 80 (3), pp. 449-457, 2014.
[6] I. E. Ebong, and P. Mazumder.”CMOS and memristor-based neural network design for position detection,” Proceedings of the IEEE, vol. 100, no. 6, pp. 2050–2060, 2011.
[7] A. U. Hassen and S. Anwar Khokhar,”Approximate in-Memory Computing on ReRAM Crossbars,” 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), Dallas, TX, USA, pp. 1183-1186, 2019.
[8] Y. Fang, C. N. Gnegy, T. Shibata, D. Dash, D. M. Chiarulli and S. P. Levitan,”Non-Boolean Associative Processing: Circuits, System Architecture, and Algorithms,” in IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, vol. 1, pp. 94-102, Dec. 2015.
[9] A. H. Kramer,”Array-based analog computation: principles, advantages and limitations.” In Proceedings of Fifth International Conference on Microelectronics for Neural Networks, pp. 68-79, 1996.
[10] L. Larger, M. C. Soriano, D. Brunner, L. Appeltant, J. M. Gutiérrez, L. Pesquera, C. R. Mirasso and I. Fischer,”Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing,” Optics express, vol. 20, no. 3, pp. 3241-3249, 2012.
[11] J. Li, Z. Qin, Y. Dai, F. Yin and K. Xu,”Real-time fourier transformation based on photonic reservior,” 2017 IEEE Photonics Conference (IPC), pp. 207-208, Orlando, FL, 2017.
[12] J. Li, K. Bai, L. Liu and Y. Yi,”A deep learning based approach for analog hardware implementation of delayed feedback reservoir computing system,” 2018 19th International Symposium on Quality Electronic Design (ISQED), pp. 308-313, Santa Clara, CA, 2018.
[13] L. Appeltant, M. C. Soriano, G. Van der Sande, J. Danckaert, S. Massar, J. Dambre, B. Schrauwen, C. R. Mirasso and I. Fischer,”Information processing using a single dynamical node as complex system,” Nature communications, no. 2, pp. 468, 2011.
[14] M. Freiberger, S. Sackesyn, C. Ma, A. Katumba, P. Bienstman and J. Dambre,”Improving Time Series Recognition and Prediction With Networks and Ensembles of Passive Photonic Reservoirs,” in IEEE Journal of Selected Topics in Quantum Electronics, vol. 26, no. 1, pp. 1-11, Art no. 7700611, Jan. -Feb. 2020.
[15] D. V. Buonomano and W. Maass,”State-dependent computations: Spatiotemporal processing in cortical networks,” Nature Reviews Neuroscience. vol. 10, no. 2, pp. 113–125, Feb. 2009.
[16] H. Jaeger and H. Haas,”Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication,” Science, vol. 304, no. 5667, pp. 78–80, 2004.
[17] E. Vassilieva, G. Pinto, J. A. De Barros, and P. Suppes.”Learning pattern recognition through quasi-synchronization of phase oscillators,” IEEE Transactions on Neural Networks, vol. 22, no. 1, pp. 84-95, 2011.
[18] Z. Wang, H. He, G. P. Jiang, J. Cao,”Quasi-Synchronization in Heterogeneous Harmonic Oscillators with Continuous and Sampled Coupling,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, Feb 22, 2019.
[19] D. A. Czaplewski, D. Antonio, J. R. Guest, D. Lopez, S. I. Arroyo and D. H. Zanette,”Enhanced synchronization range from non-linear micromechanical oscillators,” 2015 Transducers - 2015 18th International Conference on Solid-State Sensors, Actuators and Microsystems (TRANSDUCERS), pp. 2001-2004, Anchorage, AK, 2015.
[20] J. Chen, J. Lu, X. Wu and W. X. Zheng,”Impulsive synchronization on complex networks of nonlinear dynamical systems,” Proceedings of 2010 IEEE International Symposium on Circuits and Systems, Paris, pp. 421-424, 2010.
[21] H. Jaeger, and H. Haas,”Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication,” Science no. 304, pp. 78–80, 2004.
[22] W. Maass, T. Natschläger, and H. Markram,”Real-time computing without stable states: a new framework for neural computation based on perturbations,” Neural Comput. no. 14, pp. 2531–2560, 2002.
[23] C. J. Commercon, and M. Guivarch.”Current transistor-transistor-inductor oscillator,” IEEE Proceedings-Circuits, Devices and Systems, vol. 141, no. 6, pp. 498-504, 1994.
[24] E. M. Izhikevich,”Polychronization: computation with spikes,” Neural computation, vol. 18, no. 2, pp. 245-282, Feb. 2006.
[25] E. M. Izhikevich and Y. Kuramoto,”Weakly coupled oscillators,” Encyclopedia of mathematical physics, New York: Elsevier, Jan. 2006.
[26] M. Itoh, and L. O. Chua,”Star cellular neural networks for associative and dynamic memories,” International Journal of Bifurcation and Chaos, vol. 14, no. 05, pp. 1725-1772, 2004.
[27] F. C. Hoppensteadt, E. M. Izhikevich,”Oscillatory neurocomputers with dynamic connectivity,” Phys. Rev. Lett, no. 82, pp. 2983–2986, 1999.
[28] Y. Fang, V. V. Yashin, S. P. Levitan, et al.”Pattern recognition with ‘materials that compute’,” Science advances, 324 2 (9): e1601114, 2016.
[29] Y. Fang.”Hierarchical associative memory based on oscillatory neural network.” PhD diss., University of Pittsburgh, 2013.
[30] K. Veropoulos, C. Campbell, and N. Cristianini.”Controlling the sensitivity of support vector machines,” In Proceedings of the international joint conference on AI, vol. 55, p. 60. 1999.
Author Information
  • Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, the United States

  • Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, the United States

Cite This Article
  • APA Style

    Ting Zhang, Mohammad Rafiqul Haider. (2020). A Schmitt Trigger Based Oscillatory Neural Network for Reservoir Computing. Journal of Electrical and Electronic Engineering, 8(1), 1-9. https://doi.org/10.11648/j.jeee.20200801.11

    Copy | Download

    ACS Style

    Ting Zhang; Mohammad Rafiqul Haider. A Schmitt Trigger Based Oscillatory Neural Network for Reservoir Computing. J. Electr. Electron. Eng. 2020, 8(1), 1-9. doi: 10.11648/j.jeee.20200801.11

    Copy | Download

    AMA Style

    Ting Zhang, Mohammad Rafiqul Haider. A Schmitt Trigger Based Oscillatory Neural Network for Reservoir Computing. J Electr Electron Eng. 2020;8(1):1-9. doi: 10.11648/j.jeee.20200801.11

    Copy | Download

  • @article{10.11648/j.jeee.20200801.11,
      author = {Ting Zhang and Mohammad Rafiqul Haider},
      title = {A Schmitt Trigger Based Oscillatory Neural Network for Reservoir Computing},
      journal = {Journal of Electrical and Electronic Engineering},
      volume = {8},
      number = {1},
      pages = {1-9},
      doi = {10.11648/j.jeee.20200801.11},
      url = {https://doi.org/10.11648/j.jeee.20200801.11},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.jeee.20200801.11},
      abstract = {With the increase in communication bandwidth and frequency, the development level of communication technology is also constantly developing. The scale of the Internet of Things (IoT) has shifted from single point-to-point communication to mesh communication between sensors. However, the large sensors serving the infrastructure place a burden on real-time monitoring, data transmission, and even data analysis. The information processing method is experimentally demonstrated with a non-linear Schmitt trigger oscillator. A neuronally inspired concept called reservoir computing has been implemented. The synchronization frequency prediction tasks are utilized as benchmarks to reduce the computational load. The oscillator's oscillation frequency is affected by the sensor input, further affecting the storage pattern of the oscillatory neural network. This paper proposes a method of information processing by training and modulating the weights of the intrinsic electronic neural network to achieve the next step prediction. The effects on the frequency of a single oscillator in a coupled oscillatory neural network are studied under asynchronous and synchronization modes. Principle Component Analysis (PCA) is used to reduce the data dimension, and Support Vector Machine (SVM) is used to classify the synchronous and asynchronous data. We define that oscillator with stronger coupling weight (lower coupling resistance) as a leader oscillator. From the spice simulation, when OSC1 and OSC2 work as leader oscillator, the ONN almost always achieve synchronization; and the synchronization frequency is close to the average value of the leader oscillators. By training the emerging synchronous and asynchronous data, we can predict the synchronization status of an unknown dataset. Weight retrieval can be achieved by adjusting the slope and bias of the separation boundary.},
     year = {2020}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - A Schmitt Trigger Based Oscillatory Neural Network for Reservoir Computing
    AU  - Ting Zhang
    AU  - Mohammad Rafiqul Haider
    Y1  - 2020/01/04
    PY  - 2020
    N1  - https://doi.org/10.11648/j.jeee.20200801.11
    DO  - 10.11648/j.jeee.20200801.11
    T2  - Journal of Electrical and Electronic Engineering
    JF  - Journal of Electrical and Electronic Engineering
    JO  - Journal of Electrical and Electronic Engineering
    SP  - 1
    EP  - 9
    PB  - Science Publishing Group
    SN  - 2329-1605
    UR  - https://doi.org/10.11648/j.jeee.20200801.11
    AB  - With the increase in communication bandwidth and frequency, the development level of communication technology is also constantly developing. The scale of the Internet of Things (IoT) has shifted from single point-to-point communication to mesh communication between sensors. However, the large sensors serving the infrastructure place a burden on real-time monitoring, data transmission, and even data analysis. The information processing method is experimentally demonstrated with a non-linear Schmitt trigger oscillator. A neuronally inspired concept called reservoir computing has been implemented. The synchronization frequency prediction tasks are utilized as benchmarks to reduce the computational load. The oscillator's oscillation frequency is affected by the sensor input, further affecting the storage pattern of the oscillatory neural network. This paper proposes a method of information processing by training and modulating the weights of the intrinsic electronic neural network to achieve the next step prediction. The effects on the frequency of a single oscillator in a coupled oscillatory neural network are studied under asynchronous and synchronization modes. Principle Component Analysis (PCA) is used to reduce the data dimension, and Support Vector Machine (SVM) is used to classify the synchronous and asynchronous data. We define that oscillator with stronger coupling weight (lower coupling resistance) as a leader oscillator. From the spice simulation, when OSC1 and OSC2 work as leader oscillator, the ONN almost always achieve synchronization; and the synchronization frequency is close to the average value of the leader oscillators. By training the emerging synchronous and asynchronous data, we can predict the synchronization status of an unknown dataset. Weight retrieval can be achieved by adjusting the slope and bias of the separation boundary.
    VL  - 8
    IS  - 1
    ER  - 

    Copy | Download

  • Sections