IDEAS home Printed from https://ideas.repec.org/a/eee/chsofr/v161y2022ics0960077922005240.html
   My bibliography  Save this article

Boosting learning ability of overdamped bistable stochastic resonance system based physical reservoir computing model by time-delayed feedback

Author

Listed:
  • Shi, Zhuozheng
  • Liao, Zhiqiang
  • Tabata, Hitoshi

Abstract

Physical reservoir computing (RC), which can be implemented by various physical systems, is a low-cost neuromorphic framework with a fast learning capability. In the previous studies, an overdamped bistable system-based RC (OBRC) inspired by the FitzHugh-Nagumo neuron model has been proposed to construct an outstanding physical RC system. Benefitting from the stochastic resonance effect, the OBRC requires less power and has stronger noise robustness than many conventional physical RC systems. However, compared with conventional physical RC systems, its learning ability is not superior. To boost the performance of the OBRC, we propose an OBRC with time-delayed feedback (TOBRC). In this work, the TOBRC is implemented in a physical setting with time-multiplexing nodes design and simulated on a conventional computer. Moreover, we adopt a powerful optimization algorithm to automatically determine the optimal hyperparameters for both the OBRC and TOBRC; thus, a more precise quantitative discussion on the upper limit of the system can be made. To compare the TOBRC and OBRC, we conducted short-term memory and parity check tasks to assess the short-term memory ability and nonlinearity, which are the two core abilities of physical RC for learning. The results prove that the short-term memory ability and nonlinearity of the proposed TOBRC are 6.46 and 2.15 times higher than those of the OBRC, respectively. Moreover, the TOBRC outperforms the OBRC under different noise conditions. On the MNIST handwritten digit recognition benchmark, the TOBRC exhibited a lower error rate than the OBRC; it was comparable with that of advanced physical RC systems. Our study confirms that the TOBRC can exhibit excellent learning ability in practical problems.

Suggested Citation

  • Shi, Zhuozheng & Liao, Zhiqiang & Tabata, Hitoshi, 2022. "Boosting learning ability of overdamped bistable stochastic resonance system based physical reservoir computing model by time-delayed feedback," Chaos, Solitons & Fractals, Elsevier, vol. 161(C).
  • Handle: RePEc:eee:chsofr:v:161:y:2022:i:c:s0960077922005240
    DOI: 10.1016/j.chaos.2022.112314
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960077922005240
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.chaos.2022.112314?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Spagnolo, B. & Valenti, D. & Guarcello, C. & Carollo, A. & Persano Adorno, D. & Spezia, S. & Pizzolato, N. & Di Paola, B., 2015. "Noise-induced effects in nonlinear relaxation of condensed matter systems," Chaos, Solitons & Fractals, Elsevier, vol. 81(PB), pages 412-424.
    2. Qiao, Zijian & Shu, Xuedao, 2021. "Coupled neurons with multi-objective optimization benefit incipient fault identification of machinery," Chaos, Solitons & Fractals, Elsevier, vol. 145(C).
    3. Ren, Yuhao & Pan, Yan & Duan, Fabing, 2022. "SNR gain enhancement in a generalized matched filter using artificial optimal noise," Chaos, Solitons & Fractals, Elsevier, vol. 155(C).
    4. Liao, Zhiqiang & Wang, Zeyu & Yamahara, Hiroyasu & Tabata, Hitoshi, 2021. "Echo state network activation function based on bistable stochastic resonance," Chaos, Solitons & Fractals, Elsevier, vol. 153(P2).
    5. Liao, Zhiqiang & Ma, Kaijie & Tang, Siyi & Sarker, Md Shamim & Yamahara, Hiroyasu & Tabata, Hitoshi, 2021. "Phase locking of ultra-low power consumption stochastic magnetic bits induced by colored noise," Chaos, Solitons & Fractals, Elsevier, vol. 151(C).
    6. Shao, Rui-Hua & Chen, Yong, 2009. "Stochastic resonance in time-delayed bistable systems driven by weak periodic signal," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 388(6), pages 977-983.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jin, Yanfei & Wang, Heqiang, 2020. "Noise-induced dynamics in a Josephson junction driven by trichotomous noises," Chaos, Solitons & Fractals, Elsevier, vol. 133(C).
    2. Qin, Bo & Zhang, Ying, 2024. "Comprehensive analysis of the mechanism of sensitivity to initial conditions and fractal basins of attraction in a novel variable-distance magnetic pendulum," Chaos, Solitons & Fractals, Elsevier, vol. 183(C).
    3. Fang, Yuwen & Luo, Yuhui & Ma, Zhiqing & Zeng, Chunhua, 2021. "Transport and diffusion in the Schweitzer–Ebeling–Tilch model driven by cross-correlated noises," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 564(C).
    4. Li, Jun-Feng & Jahanshahi, Hadi & Kacar, Sezgin & Chu, Yu-Ming & Gómez-Aguilar, J.F. & Alotaibi, Naif D. & Alharbi, Khalid H., 2021. "On the variable-order fractional memristor oscillator: Data security applications and synchronization using a type-2 fuzzy disturbance observer-based robust control," Chaos, Solitons & Fractals, Elsevier, vol. 145(C).
    5. Chen, Ruyin & Xiong, Yue & Li, Zekun & He, Zhifen & Hou, Fang & Zhou, Jiawei, 2022. "Effects of correlated noises on binocular rivalry," Chaos, Solitons & Fractals, Elsevier, vol. 159(C).
    6. Bashkirtseva, Irina A. & Ryashko, Lev B. & Pisarchik, Alexander N., 2020. "Ring of map-based neural oscillators: From order to chaos and back," Chaos, Solitons & Fractals, Elsevier, vol. 136(C).
    7. Guarcello, C. & Bergeret, F.S., 2021. "Thermal noise effects on the magnetization switching of a ferromagnetic anomalous Josephson junction," Chaos, Solitons & Fractals, Elsevier, vol. 142(C).
    8. Duan, Wei-Long & Lin, Ling, 2021. "Noise and delay enhanced stability in tumor-immune responses to chemotherapy system," Chaos, Solitons & Fractals, Elsevier, vol. 148(C).
    9. Muhammad Zuhaib & Faraz Ahmed Shaikh & Wajiha Tanweer & Abdullah M. Alnajim & Saleh Alyahya & Sheroz Khan & Muhammad Usman & Muhammad Islam & Mohammad Kamrul Hasan, 2022. "Faults Feature Extraction Using Discrete Wavelet Transform and Artificial Neural Network for Induction Motor Availability Monitoring—Internet of Things Enabled Environment," Energies, MDPI, vol. 15(21), pages 1-32, October.
    10. Liu, Jian & Wang, Youguo, 2018. "Performance investigation of stochastic resonance in bistable systems with time-delayed feedback and three types of asymmetries," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 493(C), pages 359-369.
    11. Zhang, Ruoqi & Meng, Lin & Yu, Lei & Shi, Sihong & Wang, Huiqi, 2024. "Collective dynamics of fluctuating–damping coupled oscillators in network structures: Stability, synchronism, and resonant behaviors," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 638(C).
    12. Duan, Wei-Long, 2020. "The stability analysis of tumor-immune responses to chemotherapy system driven by Gaussian colored noises," Chaos, Solitons & Fractals, Elsevier, vol. 141(C).
    13. Yang, Jinwoong & Ryu, Hojeong & Kim, Sungjun, 2021. "Resistive and synaptic properties modulation by electroforming polarity in CMOS-compatible Cu/HfO2/Si device," Chaos, Solitons & Fractals, Elsevier, vol. 145(C).
    14. Matrozova, E.A. & Pankratov, A.L., 2023. "Noise and generation effects in parallel Josephson junction chains," Chaos, Solitons & Fractals, Elsevier, vol. 170(C).
    15. Ladeynov, D.A. & Egorov, D.G. & Pankratov, A.L., 2023. "Stochastic versus dynamic resonant activation to enhance threshold detector sensitivity," Chaos, Solitons & Fractals, Elsevier, vol. 171(C).
    16. Zhang, Dongjian & Ma, Qihua & Dong, Hailiang & Liao, He & Liu, Xiangyu & Zha, Yibin & Zhang, Xiaoxiao & Qian, Xiaomin & Liu, Jin & Gan, Xuehui, 2023. "Time-delayed feedback bistable stochastic resonance system and its application in the estimation of the Polyester Filament Yarn tension in the spinning process," Chaos, Solitons & Fractals, Elsevier, vol. 168(C).
    17. Guseinov, D.V. & Matyushkin, I.V. & Chernyaev, N.V. & Mikhaylov, A.N. & Pershin, Y.V., 2021. "Capacitive effects can make memristors chaotic," Chaos, Solitons & Fractals, Elsevier, vol. 144(C).
    18. Slepukhina, Evdokia & Bashkirtseva, Irina & Ryashko, Lev, 2020. "Stochastic spiking-bursting transitions in a neural birhythmic 3D model with the Lukyanov-Shilnikov bifurcation," Chaos, Solitons & Fractals, Elsevier, vol. 138(C).
    19. Xu, Chaoqun, 2020. "Probabilistic mechanisms of the noise-induced oscillatory transitions in a Leslie type predator-prey model," Chaos, Solitons & Fractals, Elsevier, vol. 137(C).
    20. Ryu, Ji-Ho & Kim, Sungjun, 2020. "Artificial synaptic characteristics of TiO2/HfO2 memristor with self-rectifying switching for brain-inspired computing," Chaos, Solitons & Fractals, Elsevier, vol. 140(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:chsofr:v:161:y:2022:i:c:s0960077922005240. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Thayer, Thomas R. (email available below). General contact details of provider: https://www.journals.elsevier.com/chaos-solitons-and-fractals .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.