EEG data analysis with stacked differentiable neural computers

Abstract

Differentiable neural computer (DNC) has demonstrated remarkable capabilities in solving complex problems. In this paper, we propose to stack an enhanced version of differentiable neural computer together to extend its learning capabilities. Firstly, we give an intuitive interpretation of DNC to explain the architectural essence and demonstrate the stacking feasibility by contrasting it with the conventional recurrent neural network. Secondly, the architecture of stacked DNCs is proposed and modified for electroencephalogram (EEG) data analysis. We substitute the original Long Short-Term Memory network controller by a recurrent convolutional network controller and adjust the memory accessing structures for processing EEG topographic data. Thirdly, the practicability of our proposed model is verified by an open-sourced EEG dataset with the highest average accuracy achieved; then after fine-tuning the parameters, we show the minimal mean error obtained on a proprietary EEG dataset. Finally, by analyzing the behavioral characteristics of the trained stacked DNCs model, we highlight the suitableness and potential of utilizing stacked DNCs in EEG signal processing.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

References

  1. 1.

    Graves A, Wayne G et al (2016) Hybrid computing using a neural network with dynamic external memory. Nature 538:471–476

    Article  Google Scholar 

  2. 2.

    Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge

    Google Scholar 

  3. 3.

    Lin C-T, Wu R-C, Jung T-P, Liang S-F, Huang T-Y (2005) Estimating driving performance based on EEG spectrum analysis. EURASIP J Appl Signal Process 19:3165–3174

    MATH  Google Scholar 

  4. 4.

    Sanei S (2007) EEG signal processing. Wiley, Hoboken

    Google Scholar 

  5. 5.

    Sanei S (2013) Adaptive processing of brain signals. Wiley, Hoboken

    Google Scholar 

  6. 6.

    Graves A, Wayne D, Danihelka I (2014) Neural turing machines. arXiv:1410.5401

  7. 7.

    Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: IEEE international conference on acoustics, speech and signal processing, pp 6645–6649

  8. 8.

    Gregor K, Danihelka I, Alex G, Rezende DJ, Wierstra D (2015) DRAW: a recurrent neural network for image generation. arXiv:1502.04623v2

  9. 9.

    Cho K, van Merrienboer B et al. (2014) Learning phrase representations using RNN encoder–decoder for statistical machine translation. arXiv:1406.1078

  10. 10.

    https://www.braininitiative.nih.gov/. Accessed 1 May 2018

  11. 11.

    LeCun Y, Bengio Y, Hinton G (2015) Deep learning 521:436–444

    Google Scholar 

  12. 12.

    Mizrahi EM (2014) Atlas of neonatal electroencephalography. Lippincott Williams & Wilkins, Philadelphia

    Google Scholar 

  13. 13.

    Lawhern VJ, Solon AJ, Waytowich NR, Gordon SM, Hung CP, Lance BJ (2017) EEGNet: a compact convolutional network for EEG-based brain–computer interfaces. arXiv:1611.08024v2

  14. 14.

    Konareva I (2005) Modifications of the EEG frequency pattern in humans related to a single neurofeedback session. Neurophysiology 37:388–395

    Article  Google Scholar 

  15. 15.

    Roach BJ, Mathalon DH (2008) Event-related EEG time–frequency analysis: an overview of measures and an analysis of early gamma band phase locking in schizophrenia. Schizophr Bull 34:907–926

    Article  Google Scholar 

  16. 16.

    Barry RJ, De Blasio FM (2018) EEG frequency PCA in EEG‐ERP dynamics. Psychophysiology. https://doi.org/10.1111/psyp.13042

    Article  Google Scholar 

  17. 17.

    Britz J, Van De Ville D, Michel CM (2010) BOLD correlates of EEG topography reveal rapid resting-state network dynamics. NeuroImage 52:1162–1170

    Article  Google Scholar 

  18. 18.

    Bersagliere A, Pascual-Marqui RD, Tarokh L, Achermann P (2018) Mapping slow waves by EEG topography and source localization: effects of sleep deprivation. Brain Topol 31:257–269

    Article  Google Scholar 

  19. 19.

    Bashivan P, Rish I, Yeasin M, Codella N (2016) Learning representations from EEG with deep recurrent-convolutional neural networks. In: International conference on learning representation (ICLR). arXiv:1511.06448v3

  20. 20.

    Finn C, Goodfellow I, Levine S (2016) Unsupervised learning for physical interaction through video prediction. In: Neural information processing systems (NIPS). arXiv:1605.07157v4

  21. 21.

    Chuang C-H, Ko L-W, Jung T-P, Lin C-T (2014) Kinesthesia in a sustained-attention driving task. NeuroImage 91:187–202

    Article  Google Scholar 

  22. 22.

    Hung Y-C, Wang Y-K, Prasad M, Lin C-T (2017) Brain dynamic states analysis based on 3D convolutional neural network. In: IEEE international conference on systems, man and cybernetics (SMC). https://doi.org/10.1109/smc.2017.8122606

  23. 23.

    Bear MF, Connors BW, Paradiso MA (2016) Neuroscience: exploring the brain, 4th edn. Wolters Kluwer, Alphen aan den Rijn

    Google Scholar 

  24. 24.

    Bekhtereva V, Sander C, Forschack N, Olbrich S, Hegerl U, Müller MM (2014) Effects of EEG-vigilance regulation patterns on early perceptual processes in human visual cortex. Clin Neurophysiol 125:98–107

    Article  Google Scholar 

  25. 25.

    Foucher JR, Otzenberger H, Gounot D (2004) Where arousal meets attention: a simultaneous fMRI and EEG recording study. Neuroimage 22:688–697

    Article  Google Scholar 

  26. 26.

    Olbrich S, Mulert C et al (2009) EEG-vigilance and BOLD effect during simultaneous EEG/fMRI measurement. NeuroImage 45:319–332

    Article  Google Scholar 

  27. 27.

    Kim J-H, Kim D-W, Im C-H (2017) Brain areas responsible for vigilance: an EEG source imaging study. Brain Topogr 30:343–351

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the Australian Research Council (ARC) under discovery Grant DP180100670 and DP180100656. Research was also sponsored in part by the Army Research Laboratory and was accomplished under Cooperative Agreement Number W911NF-10-2-0022 and W911NF-10-D-0002/TO 0023. The views and the conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the US Government. The US Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Chin-Teng Lin.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ming, Y., Pelusi, D., Fang, CN. et al. EEG data analysis with stacked differentiable neural computers. Neural Comput & Applic 32, 7611–7621 (2020). https://doi.org/10.1007/s00521-018-3879-1

Download citation

Keywords

  • Deep Learning (DL)
  • Differentiable neural computer (DNC)
  • Electroencephalogram (EEG)
  • Stacked DNCs