Skip to main content
SpringerLink
Log in

Hyperdimensional Computing for Blind and One-Shot Classification of EEG Error-Related Potentials

  • Published:
Mobile Networks and Applications Aims and scope Submit manuscript

Abstract

The mathematical properties of high-dimensional (HD) spaces show remarkable agreement with behaviors controlled by the brain. Computing with HD vectors, referred to as “hypervectors,” is a brain-inspired alternative to computing with numbers. HD computing is characterized by generality, scalability, robustness, and fast learning, making it a prime candidate for utilization in application domains such as brain–computer interfaces. We describe the use of HD computing to classify electroencephalography (EEG) error-related potentials for noninvasive brain–computer interfaces. Our algorithm naturally encodes neural activity recorded from 64 EEG electrodes to a single temporal–spatial hypervector without requiring any electrode selection process. This hypervector represents the event of interest, can be analyzed to identify the most discriminative electrodes, and is used for recognition of the subject’s intentions. Using the full set of training trials, HD computing achieves on average 5% higher single-trial classification accuracy compared to a conventional machine learning method on this task (74.5% vs. 69.5%) and offers further advantages: (1) Our algorithm learns fast: using only 34% of training trials it achieves an average accuracy of 70.5%, surpassing the conventional method. (2) Conventional method requires prior domain expert knowledge, or a separate process, to carefully select a subset of electrodes for a subsequent preprocessor and classifier, whereas our algorithm blindly uses all 64 electrodes, tolerates noises in data, and the resulting hypervector is intrinsically clustered into HD space; in addition, most preprocessing of the electrode signal can be eliminated while maintaining an average accuracy of 71.7%.

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. MATLAB code for our encoding algorithm and classifier is open access and available at https://github.com/abbas-rahimi/HDC-EEG-ERP.

  2. For S4, we double the length of slices (16 samples in each) that results in 19 slices to cover the window instead of 38.

  3. Equation 5 for the spatial encoder is limited to one or two electrode(s) and the CAR filter is applied before the BPF.

References

  1. BNCI Horizon 2020. http://bnci-horizon-2020.eu/

  2. Monitoring error-related potentials. http://bnci-horizon-2020.eu/database/data-sets

  3. Bertrand O, Perrin F, Pernier J (1985) A theoretical justification of the average reference in topographic evoked potential studies. Electroencephalography and Clinical Neurophysiology/Evoked Potentials Section 62 (6):462–464. https://doi.org/10.1016/0168-5597(85)90058-9. http://www.sciencedirect.com/science/article/pii/0168559785900589

  4. Chavarriaga R, Millán JDR (2010) Learning from eeg error-related potentials in noninvasive brain-computer interfaces. IEEE Trans Neural Syst Rehabil Eng 18(4):381–388.

    Article  Google Scholar 

  5. Ferrez P, Millán JDR (2007) Error-related EEG potentials in brain-computer interfaces. Ph.D. thesis, STI, Lausanne. https://doi.org/10.5075/epfl-thesis-3928

  6. Ferrez PW, Millán JDR (2005) You are wrong!—automatic detection of interaction errors from brain waves. In: Proceedings of the 19th international joint conference on artificial intelligence

  7. Ferrez PW, Millán JDR (2008) Error-related eeg potentials generated during simulated brain-computer interaction. IEEE Trans Biomed Eng 55(3):923–929. https://doi.org/10.1109/TBME.2007.908083

    Article  Google Scholar 

  8. Gayler RW (1998) Multiplicative binding, representation operators & analogy. Advances in analogy research

  9. He X, Cai D, Niyogi P (2005) Laplacian score for feature selection. In: Proceedings of the 18th international conference on neural information processing systems, NIPS’05. MIT Press, Cambridge, pp 507–514. http://dl.acm.org/citation.cfm?id=2976248.2976312

  10. Hsu J (2014) Ibm’s new brain [news]. IEEE Spectr 51(10):17–19. https://doi.org/10.1109/MSPEC.2014.6905473

    Article  MathSciNet  Google Scholar 

  11. Joshi A, Halseth J, Kanerva P (2017) Language geometry using random indexing. In: de Barros JA, Coecke B, Pothos E (eds) 10th international conference on quantum interaction, QI 2016. Springer, pp 265–274

  12. Kanerva P (1988) Sparse distributed memory. MIT Press, Cambridge

    MATH  Google Scholar 

  13. Kanerva P (2009) Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cogn Comput 1(2):139–159. https://doi.org/10.1007/s12559-009-9009-8

    Article  Google Scholar 

  14. Kanerva P (2010) What we mean when we say “what’s the dollar of mexico?”: prototypes and mapping in concept space. In: AAAI fall symposium: quantum informatics for cognitive, social, and semantic processes, pp 2–6

  15. Kanerva P (2014) Computing with 10,000-bitwords. In: Proceedings of the 52nd annual allerton conference on communication, control, and computing

  16. Kanerva P, Kristoferson J, Holst A (2000) Random indexing of text samples for latent semantic analysis. In: Proceedings of the 22nd annual conference of the cognitive science society. Erlbaum, pp 103–6

  17. Li H et al (2016) Hyperdimensional computing with 3d vrram in-memory kernels: device-architecture co-design for energy-efficient, error-resilient language recognition. IEEE International Electron Devices Meeting

  18. McFarland DJ, McCane LM, David SV, Wolpaw JR (1997) Spatial filter selection for eeg-based communication. Electroencephalogr Clin Neurophysiol 103 (3):386–394. https://doi.org/10.1007/s12559-009-9009-8. http://www.sciencedirect.com/science/article/pii/S0013469497000222

    Article  Google Scholar 

  19. Najafabadi FR, Rahimi A, Kanerva P, Rabaey JM (2016) Hyperdimensional computing for text classification. Design, automation test in europe conference exhibition (DATE), University Booth. https://www.date-conference.com/system/files/file/date16/ubooth/37923.pdf

  20. Nishihara K, TAYA N, KANOH T (2016) A consideration of realizing the brain inspired computer. In: Proceedings of the 9th EAI international conference on bio-inspired information and communications technologies (formerly BIONETICS), BICT’15. ICST, Brussels, pp 495–496. https://doi.org/10.4108/eai.3-12-2015.2262461

  21. Rahimi A, Benatti S, Kanerva P, Benini L, Rabaey JM (2016) Hyperdimensional biosignal processing: a case study for emg-based hand gesture recognition. In: IEEE international conference on rebooting computing

  22. Rahimi A, Kanerva P, Millán JDR, Rabaey JM (2017) Hyperdimensional computing for noninvasive brain–computer interfaces: blind and one-shot classification of eeg error-related potentials. In: 10th EAI international conference on bio-inspired information and communications technologies (BICT)

  23. Rahimi A, Kanerva P, Rabaey JM (2016) A robust and energy efficient classifier using brain-inspired hyperdimensional computing. In: 2016 IEEE/ACM international symposium on low power electronics and design (ISLPED)

  24. Sahlgren M (2005) An introduction to random indexing. In: In methods and applications of semantic indexing workshop at the 7th international conference on terminology and knowledge engineering, TKE 2005

  25. Widdows D, Bing M (2014) Reasoning with vectors: a continuous model for fast robust inference. In: Logic journal of the IGPL

Download references

Acknowledgements

This work was supported by Systems on Nanoscale Information fabriCs (SONIC), one of the six SRC STARnet Centers, sponsored by MARCO and DARPA, and by Intel Strategic Research Alliance (ISRA) program on Neuromorphic Architectures for Mainstream Computing.

Author information

Authors and Affiliations

  1. Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, 94720, USA

    Abbas Rahimi & Jan M. Rabaey

  2. STMicroelectronics, Crolles, France

    Artiom Tchouprina

  3. Berkeley Wireless Research Center, Berkeley, CA, 94704, USA

    Artiom Tchouprina

  4. Redwood Center for Theoretical Neuroscience, University of California Berkeley, Berkeley, CA, 94720, USA

    Pentti Kanerva

  5. Defitech Foundation Chair in Brain-Machine Interface, Ecole Polytechnique Fédérale de Lausanne (EPFL), 1015, Lausanne, Switzerland

    José del R. Millán

Authors
  1. Abbas Rahimi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Artiom Tchouprina
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pentti Kanerva
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. José del R. Millán
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jan M. Rabaey
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Abbas Rahimi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rahimi, A., Tchouprina, A., Kanerva, P. et al. Hyperdimensional Computing for Blind and One-Shot Classification of EEG Error-Related Potentials. Mobile Netw Appl 25, 1958–1969 (2020). https://doi.org/10.1007/s11036-017-0942-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11036-017-0942-6

Keywords

Search

Navigation