Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

A memristor-based adaptive neuromorphic decoder for brain–computer interfaces

Nature Electronics volume 8, pages 362–372 (2025)Cite this article

Subjects

Abstract

Practical brain–computer interfaces should be able to decipher brain signals and dynamically adapt to brain fluctuations. This, however, requires a decoder capable of flexible updates with energy-efficient decoding capabilities. Here we report a neuromorphic and adaptive decoder for brain–computer interfaces, which is based on a 128k-cell memristor chip. Our approach features a hardware-efficient one-step memristor decoding strategy that allows the interface to achieve software-equivalent decoding performance. Furthermore, we show that the system can be used for the real-time control of a drone in four degrees of freedom. We also develop an interactive update framework that allows the memristor decoder and the changing brain signals to adapt to each other. We illustrate the capabilities of this co-evolution of the brain and memristor decoder over an extended interaction task involving ten participants, which leads to around 20% higher accuracy than an interface without co-evolution.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Schematic of BCI with brain–memristor decoder co-evolution.
Fig. 2: Design of a memristor-chip-enabled BCI.
Fig. 3: Real-time brain-controlled drone flight with a memristor-chip-based decoder.
Fig. 4: Online brain–memristor decoder co-evolution experiments with HLU.

Similar content being viewed by others

Data availability

Source data are provided with this paper. Other data that support the findings of this study are available from the corresponding authors upon reasonable request.

Code availability

The core code for memristor-based one-step decoding is publicly available via GitHub at https://github.com/zhengwuliu/Memristor_Co-evoutional_BCI. Other code that supports the findings of this study is available from the corresponding authors upon reasonable request.

References

  1. Willett, F. R., Avansino, D. T., Hochberg, L. R., Henderson, J. M. & Shenoy, K. V. High-performance brain-to-text communication via handwriting. Nature 593, 249–254 (2021).

    Article  Google Scholar 

  2. Anumanchipalli, G. K., Chartier, J. & Chang, E. F. Speech synthesis from neural decoding of spoken sentences. Nature 568, 493–498 (2019).

    Article  Google Scholar 

  3. Metzger, S. L. et al. A high-performance neuroprosthesis for speech decoding and avatar control. Nature 620, 1037–1046 (2023).

    Article  Google Scholar 

  4. Willett, F. R. et al. A high-performance speech neuroprosthesis. Nature 620, 1031–1036 (2023).

    Article  Google Scholar 

  5. Flesher, S. N. et al. A brain–computer interface that evokes tactile sensations improves robotic arm control. Science 372, 831–836 (2021).

  6. Lorach, H. et al. Walking naturally after spinal cord injury using a brain–spine interface. Nature 618, 126–133 (2023).

  7. Silversmith, D. B. et al. Plug-and-play control of a brain–computer interface through neural map stabilization. Nat. Biotechnol. 39, 326–335 (2021).

    Article  Google Scholar 

  8. Chiang, K.-J., Wei, C.-S., Nakanishi, M. & Jung, T.-P. Boosting template-based SSVEP decoding by cross-domain transfer learning. J. Neural Eng. 18, 016002 (2021).

    Article  Google Scholar 

  9. Pascual-Leone, A., Amedi, A., Fregni, F. & Merabet, L. B. The plastic human brain cortex. Annu. Rev. Neurosci. 28, 377–401 (2005).

    Article  Google Scholar 

  10. Luppi, A. I. et al. A synergistic core for human brain evolution and cognition. Nat. Neurosci. 25, 771–782 (2022).

    Article  Google Scholar 

  11. Abbott, L. F. & Nelson, S. B. Synaptic plasticity: taming the beast. Nat. Neurosci. 3, 1178–1183 (2000).

    Article  Google Scholar 

  12. Sur, M. & Rubenstein, J. L. R. Patterning and plasticity of the cerebral cortex. Science 310, 805–810 (2005).

    Article  Google Scholar 

  13. Holz, E. M., Botrel, L., Kaufmann, T. & Kübler, A. Long-term independent brain–computer interface home use improves quality of life of a patient in the locked-in state: a case study. Arch. Phys. Med. Rehabil. 96, S16–S26 (2015).

  14. Sussillo, D., Stavisky, S. D., Kao, J. C., Ryu, S. I. & Shenoy, K. V. Making brain–machine interfaces robust to future neural variability. Nat. Commun. 7, 13749 (2016).

    Article  Google Scholar 

  15. Wen, S. et al. Rapid adaptation of brain–computer interfaces to new neuronal ensembles or participants via generative modelling. Nat. Biomed. Eng. 7, 546–558 (2023).

    Article  Google Scholar 

  16. Renart, A. & Machens, C. K. Variability in neural activity and behavior. Curr. Opin. Neurobiol. 25, 211–220 (2014).

    Article  Google Scholar 

  17. van Praag, H., Kempermann, G. & Gage, F. H. Neural consequences of enviromental enrichment. Nat. Rev. Neurosci. 1, 191–198 (2000).

    Article  Google Scholar 

  18. Wolpaw, J. R. Brain–computer interfaces as new brain output pathways. J. Physiol. 579, 613–619 (2007).

    Article  Google Scholar 

  19. Musk, E. An integrated brain–machine interface platform with thousands of channels. J. Med. Internet Res. 21, e16194 (2019).

  20. Sahasrabuddhe, K. et al. The Argo: a high channel count recording system for neural recording in vivo. J. Neural Eng. 18, 015002 (2021).

    Article  Google Scholar 

  21. Steinmetz, N. A. et al. Neuropixels 2.0: a miniaturized high-density probe for stable, long-term brain recordings. Science 372, eabf4588 (2021).

  22. Grover, P. & Venkatesh, P. An information-theoretic view of EEG sensing. Proc. IEEE 105, 367–384 (2016).

    Article  Google Scholar 

  23. Han, J. et al. A high-speed hybrid brain–computer interface with more than 200 targets. J. Neural Eng. 20, 016025 (2023).

  24. Chen, Y. et al. Implementing a calibration-free SSVEP-based BCI system with 160 targets. J. Neural Eng. 18, 046094 (2021).

    Article  Google Scholar 

  25. Horowitz, M. 1.1 Computing’s energy problem (and what we can do about it). In 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC) 10–14 (IEEE, 2014).

  26. Dethier, J., Nuyujukian, P., Ryu, S. I., Shenoy, K. V. & Boahen, K. Design and validation of a real-time spiking-neural-network decoder for brain–machine interfaces. J. Neural Eng. 10, 036008 (2013).

  27. Boi, F. et al. A bidirectional brain–machine interface featuring a neuromorphic hardware decoder. Front. Neurosci. 10, 563 (2016).

  28. Shaikh, S., So, R., Sibindi, T., Libedinsky, C. & Basu, A. Real-time closed loop neural decoding on a neuromorphic chip. In 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER) 670–673 (IEEE, 2019).

  29. Sharifshazileh, M., Burelo, K., Sarnthein, J. & Indiveri, G. An electronic neuromorphic system for real-time detection of high frequency oscillations (HFO) in intracranial EEG. Nat. Commun. 12, 3095 (2021).

    Article  Google Scholar 

  30. Ambrogio, S. et al. Equivalent-accuracy accelerated neural-network training using analogue memory. Nature 558, 60–67 (2018).

    Article  Google Scholar 

  31. Wan, W. et al. A compute-in-memory chip based on resistive random-access memory. Nature 608, 504–512 (2022).

    Article  Google Scholar 

  32. Xia, Q. & Yang, J. J. Memristive crossbar arrays for brain-inspired computing. Nat. Mater. 18, 309–323 (2019).

    Article  Google Scholar 

  33. Guo, Z. et al. An emerging NVM CIM accelerator with shared-path transpose read and bit-interleaving weight storage for efficient on-chip training in edge devices. In IEEE Transactions on Circuits and Systems II: Express Briefs 2645–2649 (IEEE, 2023).

  34. Gao, B. et al. Memristor-based analogue computing for brain-inspired sound localization with in situ training. Nat. Commun. 13, 2026 (2022).

    Article  Google Scholar 

  35. Zhang, W. et al. Edge learning using a fully integrated neuro-inspired memristor chip. Science 381, 1205–1211 (2023).

    Article  Google Scholar 

  36. Liu, Z. et al. Neural signal analysis with memristor arrays towards high-efficiency brain–machine interfaces. Nat. Commun. 11, 4234 (2020).

    Article  Google Scholar 

  37. Liu, Z. et al. Multichannel parallel processing of neural signals in memristor arrays. Sci. Adv. 6, eabc4797 (2020).

    Article  Google Scholar 

  38. Yuan, R. et al. A neuromorphic physiological signal processing system based on VO2 memristor for next-generation human–machine interface. Nat. Commun. 14, 3695 (2023).

  39. Lee, D. et al. Oxide based nanoscale analog synapse device for neural signal recognition system. In 2015 IEEE International Electron Devices Meeting (IEDM) 4.7.1–4.7.4 (IEEE, 2015).

  40. Park, S. et al. Electronic system with memristive synapses for pattern recognition. Sci. Rep. 5, 10123 (2015).

    Article  Google Scholar 

  41. Zhu, X., Wang, Q. & Lu, W. D. Memristor networks for real-time neural activity analysis. Nat. Commun. 11, 2439 (2020).

    Article  Google Scholar 

  42. Gupta, I. et al. Real-time encoding and compression of neuronal spikes by metal-oxide memristors. Nat. Commun. 7, 12805 (2016).

    Article  Google Scholar 

  43. Chen, X. et al. High-speed spelling with a noninvasive brain–computer interface. Proc. Natl Acad. Sci. USA 112, E6058–E6067 (2015).

    Article  Google Scholar 

  44. Mahmood, M. et al. Fully portable and wireless universal brain–machine interfaces enabled by flexible scalp electronics and deep learning algorithm. Nat. Mach. Intell. 1, 412–422 (2019).

    Article  Google Scholar 

  45. Chiang, K.-J. et al. A closed-loop adaptive brain-computer interface framework: improving the classifier with the use of error-related potentials. In 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER) 487–490 (IEEE, 2021).

  46. Chavarriaga, R., Sobolewski, A. & Millán, J. D. R. Errare machinale est: the use of error-related potentials in brain-machine interfaces. Front. Neurosci. 8, 208 (2014).

  47. Chavarriaga, R. & Millan, J. D. R. Learning from EEG error-related potentials in noninvasive brain-computer interfaces. IEEE Trans. Neural Syst. Rehabil. Eng. 18, 381–388 (2010).

    Article  Google Scholar 

  48. Nakanishi, M. et al. Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis. IEEE Trans. Biomed. Eng. 65, 104–112 (2018).

    Article  Google Scholar 

  49. Gulati, T., Guo, L., Ramanathan, D. S., Bodepudi, A. & Ganguly, K. Neural reactivations during sleep determine network credit assignment. Nat. Neurosci. 20, 1277–1284 (2017).

    Article  Google Scholar 

  50. Müller, J. S. et al. A mathematical model for the two-learners problem. J. Neural Eng. 14, 036005 (2017).

    Article  Google Scholar 

  51. Orsborn, A. L. et al. Closed-loop decoder adaptation shapes neural plasticity for skillful neuroprosthetic control. Neuron 82, 1380–1393 (2014).

    Article  Google Scholar 

  52. Madduri, M. M., Burden, S. A. & Orsborn, A. L. Biosignal-based co-adaptive user-machine interfaces for motor control. Curr. Opin. Biomed. Eng. 27, 100462 (2023).

    Article  Google Scholar 

  53. Shanechi, M. M. et al. Rapid control and feedback rates enhance neuroprosthetic control. Nat. Commun. 8, 13825 (2017).

    Article  Google Scholar 

  54. Ahmadipour, P., Yang, Y., Chang, E. F. & Shanechi, M. M. Adaptive tracking of human ECoG network dynamics. J. Neural Eng. 18, 016011 (2021).

    Google Scholar 

  55. Meidahl, A. C. et al. Adaptive deep brain stimulation for movement disorders: the long road to clinical therapy. Mov. Disord. 32, 810–819 (2017).

    Article  Google Scholar 

  56. Shin, U. et al. NeuralTree: a 256-channel 0.227-μJ/class versatile neural activity classification and closed-loop neuromodulation SoC. IEEE J. Solid-State Circuits 57, 3243–3257 (2022).

    Article  Google Scholar 

  57. Xiao, X. et al. Discriminative canonical pattern matching for single-trial classification of ERP components. IEEE Trans. Biomed. Eng. 67, 2266–2275 (2019).

    Article  Google Scholar 

  58. Luo, R. et al. Data augmentation of SSVEPs using source aliasing matrix estimation for brain-computer interfaces. IEEE Trans. Biomed. Eng. 70, 1775–1785 (2023).

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the STI 2030-Major Projects 2022ZD0210200 (J.T.), National Natural Science Foundation of China (nos. 92264201 (J.T.), 62025111 (H.W.), 82330064 (M.X.), 62122059 (M.X.), 81925020 (D.M.), 62206198 (K.W.) and 62404187 (Z.L.)), the XPLORER Prize (H.W.), the Theme-based Research Scheme (TRS) project T45-701/22-R (N.W.), the Seed Fund for Basic Research from the University of Hong Kong (Z.L.) and the Center of Nanofabrication (Tsinghua University).

Author information

Author notes

  1. These authors contributed equally: Zhengwu Liu, Jie Mei.

Authors and Affiliations

  1. School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, Tsinghua University, Beijing, China

    Zhengwu Liu, Jianshi Tang, Bin Gao, Sanchuang Ding, Qi Liu, Qi Qin, Yue Xi, Yijun Li, Peng Yao, Han Zhao, He Qian & Huaqiang Wu

  2. Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China

    Zhengwu Liu & Ngai Wong

  3. Academy of Medical Engineering and Translational Medicine, Medical School, Tianjin University, Tianjin, China

    Jie Mei, Minpeng Xu, Kun Wang, Weize Chen, Tzyy-Ping Jung & Dong Ming

  4. State Key Laboratory of Advanced Medical Materials and Devices, Tianjin, China

    Jie Mei & Weize Chen

  5. Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China

    Jianshi Tang, Bin Gao, He Qian & Huaqiang Wu

  6. Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration, Tianjin, China

    Minpeng Xu, Kun Wang & Dong Ming

  7. Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China

    Bo Hong

  8. Swartz Center for Computational Neuroscience, University of California San Diego, San Diego, CA, USA

    Tzyy-Ping Jung

Authors
  1. Zhengwu Liu
    View author publications

    Search author on:PubMed Google Scholar

  2. Jie Mei
    View author publications

    Search author on:PubMed Google Scholar

  3. Jianshi Tang
    View author publications

    Search author on:PubMed Google Scholar

  4. Minpeng Xu
    View author publications

    Search author on:PubMed Google Scholar

  5. Bin Gao
    View author publications

    Search author on:PubMed Google Scholar

  6. Kun Wang
    View author publications

    Search author on:PubMed Google Scholar

  7. Sanchuang Ding
    View author publications

    Search author on:PubMed Google Scholar

  8. Qi Liu
    View author publications

    Search author on:PubMed Google Scholar

  9. Qi Qin
    View author publications

    Search author on:PubMed Google Scholar

  10. Weize Chen
    View author publications

    Search author on:PubMed Google Scholar

  11. Yue Xi
    View author publications

    Search author on:PubMed Google Scholar

  12. Yijun Li
    View author publications

    Search author on:PubMed Google Scholar

  13. Peng Yao
    View author publications

    Search author on:PubMed Google Scholar

  14. Han Zhao
    View author publications

    Search author on:PubMed Google Scholar

  15. Ngai Wong
    View author publications

    Search author on:PubMed Google Scholar

  16. He Qian
    View author publications

    Search author on:PubMed Google Scholar

  17. Bo Hong
    View author publications

    Search author on:PubMed Google Scholar

  18. Tzyy-Ping Jung
    View author publications

    Search author on:PubMed Google Scholar

  19. Dong Ming
    View author publications

    Search author on:PubMed Google Scholar

  20. Huaqiang Wu
    View author publications

    Search author on:PubMed Google Scholar

Contributions

J.T., M.X., D.M. and H.W. supervised the project. Z.L., J.M., J.T., M.X., D.M. and H.W. conceived the idea. Z.L., J.M., J.T. and M.X. designed the experiments and wrote the paper. Q.L., J.T., B.G., H.Q. and H.W. contributed to the design and fabrication of the memristor chip. Z.L., S.D. and Q.Q. designed the chip test system. Z.L., Y.X. and Y.L. tested and characterized the memristor devices. Z.L., J.M., J.T. and M.X. designed the interactive co-evolution scheme. Z.L. and J.T. designed the memristor-related algorithms and implemented them on the co-evolution BCI system. J.M., M.X. and W.C. designed the co-evolution BCI software at the PC end and implemented the electroencephalogram decoding algorithm. J.M., M.X., K.W. and W.C. designed the BCI paradigm. J.M. collected the brain signals for the simulated online experiments. Z.L. developed and implemented the one-step decoding models on memristor chips. Z.L. and J.M. performed the memristor-chip-based brain-controlled drone flight experiments. Z.L., J.M. and W.C. performed the brain–memristor decoder co-evolution experiments. P.Y., H.Z., N.W., B.H. and T.-P.J. discussed the results and benchmark. All authors commented on the paper.

Corresponding authors

Correspondence to Jianshi Tang, Minpeng Xu, Dong Ming or Huaqiang Wu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Electronics thanks Shuo Gao and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 Analog resistive switching characteristics of memristors.

a, Direct-current (DC) I-V curves of a typical memristor device. The red and green lines plot the mean values of 50 consecutive switching cycles, which are indicated by grey lines. b, Analog resistive switching characteristics for 128 representative memristor devices under 10 consecutive pulsed SET and RESET cycles. The read voltage is fixed at 0.2 V. Data are presented as mean values ± s.d.

Extended Data Fig. 2 Binary masks for parameter pruning experiments.

a, Mask for parameters whose magnitudes are at the top 5%, b, Mask for parameters whose magnitudes are at the top 20%, b, Mask for parameters whose magnitudes are at the top 40%, d, Mask examples for single-channel decoding experiments. Here the activated channels for subjects A1-A5 are channels PO5, POz, PO6, O1 and O2, respectively.

Extended Data Fig. 3 Results of SU experiments for brain-memristor decoder co-evolution.

a, Decoding accuracies over 5 update cycles for the BCIs with (w/) and without (w/o) co-evolution. b, Adaptive memristor decoder map after each update cycle. c, Correlation coefficients between each decoder map and the final one. d, Correlation coefficients between the decoder maps for each channel.

Extended Data Fig. 4 Overall performance of the ErrP detector.

a, Average TPR, TNR and BACC as a function of the number of samples (n = 100, 200, 300, 500, 700, and 1000) in the training set, and the testing set contains 360 samples. The samples in the training set and testing set are randomly selected from the data collected in the ErrP calibration experiment without overlap. b, Average TPR, TNR and BACC as a function of the classification threshold. If the feature value of the DCPM-based classifier exceeds a predefined threshold, it labels the classification of “target”; otherwise, it labels the classification of “non-target”. These metrics are calculated from the leave-one-block-out cross-validation on the training data. c, Confusion matrix between the “target” class and the “non-target” class when the threshold is set as 0.5 in b. d, Grand averaged metrics on 10 blocks online data from all 10 subjects (n = 100). The error bars in a and d, and the shaded areas in b indicate the mean values ± s.d. e, Correct and incorrect evoked signals from channel FCZ (green and red lines, respectively). The shade areas in e indicate the 95% confidence intervals.

Extended Data Fig. 5 Accuracy evolution for BCIs with and without co-evolution for 10 subjects.

a-j, Decoding accuracy results for subjects B1-B10, respectively.

Extended Data Table 1 Command encoding for the 4-DOF brain-controlled drone flight
Full size table
Extended Data Table 2 Decoding results by the memristor chip and CPU for 5 different subjects
Full size table
Extended Data Table 3 Benchmark of energy consumption and area for the memristor chip-based decoder
Full size table
Extended Data Table 4 Pruning experiments with masks on the decoder parameters
Full size table

Supplementary information

Supplementary Information

Supplementary Figs. 1–15 and Tables 1–4.

Reporting Summary

Supplementary Video 1

Real-time brain-controlled drone flight with the memristor-enabled neuromorphic BCI.

Source data

Source Data Figs. 2–4

Source data for Figs. 2–4.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Z., Mei, J., Tang, J. et al. A memristor-based adaptive neuromorphic decoder for brain–computer interfaces. Nat Electron 8, 362–372 (2025). https://doi.org/10.1038/s41928-025-01340-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41928-025-01340-2

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing