Skip to main content
SpringerLink
Log in

Associative learning of a three-terminal memristor network for digits recognition

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Imitating the associative intelligence of the biological brain is attractive but is poorly achieved in hardware because the complex tunable connection in neural networks is difficult to reproduce. We develop a circuit composed of a three-terminal memristor network to reproduce the biological conditioning process artificially. The synaptic weight between co-firing neurons is strengthened simultaneously by generating a feedback signal from the integrate-and-fire neuron to the gate of the synaptic memristor. The network allows the multi-associative capacity of recalling more than one digit in one circuit. Both single and multi-associative learning for recalling digital images are achieved. Furthermore, all 10 digital images from “0” to “9” are successfully recalled in an associative network with such paralleling circuits. Assisted by this associative layer, a typical classification network effectively improves the recognition rate for fragmentary digital images. Our work sheds light on brain-inspired artificial associative memory and provides a strategy for applications, such as object recognition with partial features and similar scenes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Kohonen T, Reuhkala E, Mäkisara K, et al. Associative recall of images. Biol Cybern, 1976, 22: 159–168

    Article  Google Scholar 

  2. Kohonen T. Adaptive, associative, and self-organizing functions in neural computing. Appl Opt, 1987, 26: 4910–4918

    Article  Google Scholar 

  3. Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA, 1982, 79: 2554–2558

    Article  MathSciNet  Google Scholar 

  4. Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA, 1984, 81: 3088–3092

    Article  Google Scholar 

  5. Hopfield J J, Tank D W. Computing with neural circuits: a model. Science, 1986, 233: 625–633

    Article  Google Scholar 

  6. Hu S G, Liu Y, Liu Z, et al. Associative memory realized by a reconfigurable memristive Hopfield neural network. Nat Commun, 2015, 6: 7522

    Article  Google Scholar 

  7. Yang J, Wang L, Wang Y, et al. A novel memristive Hopfield neural network with application in associative memory. Neurocomputing, 2017, 227: 142–148

    Article  Google Scholar 

  8. Zhou Y, Wu H, Gao B, et al. Associative memory for image recovery with a high-performance memristor array. Adv Funct Mater, 2019, 29: 1900155

    Article  Google Scholar 

  9. Cai F, Kumar S, van Vaerenbergh T, et al. Power-efficient combinatorial optimization using intrinsic noise in memristor Hopfield neural networks. Nat Electron, 2020, 3: 409–418

    Article  Google Scholar 

  10. Kosko B. Adaptive bidirectional associative memories. Appl Opt, 1987, 26: 4947–4960

    Article  Google Scholar 

  11. Hasan S M R, Siong N K. A VLSI BAM neural network chip for pattern recognition applications. In: Proceedings of International Conference on Neural Networks, 1995. 1: 164–168

  12. Pavlov I P. Conditioned Reflexes. London: Oxford University Press, 1927. 1–448

    Google Scholar 

  13. Yao P, Wu H, Gao B, et al. Fully hardware-implemented memristor convolutional neural network. Nature, 2020, 577: 641–646

    Article  Google Scholar 

  14. Zhu J, Zhang T, Yang Y, et al. A comprehensive review on emerging artificial neuromorphic devices. Appl Phys Rev, 2020, 7: 011312

    Article  Google Scholar 

  15. Zhang W, Gao B, Tang J, et al. Neuro-inspired computing chips. Nat Electron, 2020, 3: 371–382

    Article  Google Scholar 

  16. Fuller E J, Keene S T, Melianas A, et al. Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing. Science, 2019, 364: 570–574

    Article  Google Scholar 

  17. Wang Z, Wu H, Burr G W, et al. Resistive switching materials for information processing. Nat Rev Mater, 2020, 5: 173–195

    Article  Google Scholar 

  18. Tian B B, Zhong N, Duan C G. Recent advances, perspectives, and challenges in ferroelectric synapses. Chin Phys B, 2020, 29: 097701

    Article  Google Scholar 

  19. Li Y, Lu J, Shang D, et al. Oxide-based electrolyte-gated transistors for spatiotemporal information processing. Adv Mater, 2020, 32: 2003018

    Article  Google Scholar 

  20. Tian B, Liu L, Yan M, et al. A robust artificial synapse based on organic ferroelectric polymer. Adv Electron Mater, 2019, 5: 1800600

    Article  Google Scholar 

  21. Yan M, Zhu Q, Wang S, et al. Ferroelectric synaptic transistor network for associative memory. Adv Electron Mater, 2021, 7: 2001276

    Article  Google Scholar 

  22. Kim M K, Lee J S. Ferroelectric analog synaptic transistors. Nano Lett, 2019, 19: 2044–2050

    Article  Google Scholar 

  23. Niu X, Tian B, Zhu Q, et al. Ferroelectric polymers for neuromorphic computing. Appl Phys Rev, 2022, 9: 021309

    Article  Google Scholar 

  24. Zhou F, Zhou Z, Chen J, et al. Optoelectronic resistive random access memory for neuromorphic vision sensors. Nat Nanotechnol, 2019, 14: 776–782

    Article  Google Scholar 

  25. Lao J, Yan M, Tian B, et al. Ultralow-power machine vision with self-powered sensor reservoir. Adv Sci, 2022, 9: 2106092

    Article  Google Scholar 

  26. Cui B, Fan Z, Li W, et al. Ferroelectric photosensor network: an advanced hardware solution to real-time machine vision. Nat Commun, 2022, 13: 1707

    Article  Google Scholar 

  27. Cai Y, Zhang J, Yan M, et al. Molecular ferroelectric/semiconductor interfacial memristors for artificial synapses. npj Flex Electron, 2022, 6: 16

    Article  Google Scholar 

  28. Wang S, Wang C Y, Wang P, et al. Networking retinomorphic sensor with memristive crossbar for brain-inspired visual perception. Natl Sci Rev, 2020, 8: nwaa172

    Article  Google Scholar 

  29. Rashid T. Make Your Own Neural Network. North Charleston: CreateSpace Independent Publishing Platform, 2016. 105–121

    Google Scholar 

  30. Bu X, Xu H, Shang D, et al. Ion-gated transistor: an enabler for sensing and computing integration. Adv Intelligent Syst, 2020, 2: 2000156

    Article  Google Scholar 

  31. Feng G, Jiang J, Li Y, et al. Flexible vertical photogating transistor network with an ultrashort channel for in-sensor visual nociceptor. Adv Funct Mater, 2021, 31: 2104327

    Article  Google Scholar 

  32. Ren Y, Yang J, Zhou L, et al. Gate-tunable synaptic plasticity through controlled polarity of charge trapping in fullerene composites. Adv Funct Mater, 2018, 28: 1805599

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by National Key Research and Development Program of China (Grant No. 2021YFA1200700), National Natural Science Foundation of China (Grant No. 62174053), Open Research Projects of Zhejiang Lab (Grant No. 2021MD0AB03), Shanghai Science and Technology Innovation Action Plan (Grant Nos. 21520714100, 19JC1416700), Shanghai Pujiang Program (Grant No. 19PJ1402900), and Fundamental Research Funds for the Central Universities.

Author information

Authors and Affiliations

  1. Key Laboratory of Polar Materials and Devices (MOE), Ministry of Education, Department of Electronics, East China Normal University, Shanghai, 200241, China

    Yiming Ren, Bobo Tian, Mengge Yan, Guangdi Feng, Fangyu Yue, Hui Peng, Xiaodong Tang, Qiuxiang Zhu, Junhao Chu & Chungang Duan

  2. Zhejiang Lab, Hangzhou, 310000, China

    Bobo Tian & Qiuxiang Zhu

  3. Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, 100084, China

    Bin Gao

  4. Collaborative Innovation Center of Extreme Optics, Shanxi University, Shanxi, 030006, China

    Chungang Duan

Authors
  1. Yiming Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bobo Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengge Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guangdi Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bin Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Fangyu Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hui Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiaodong Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Qiuxiang Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Junhao Chu
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Chungang Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Bobo Tian or Qiuxiang Zhu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ren, Y., Tian, B., Yan, M. et al. Associative learning of a three-terminal memristor network for digits recognition. Sci. China Inf. Sci. 66, 122403 (2023). https://doi.org/10.1007/s11432-022-3503-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11432-022-3503-4

Keywords

Search

Navigation