Papers
Topics
Authors
Recent
Search
2000 character limit reached

Sparse Multitask Learning for Efficient Neural Representation of Motor Imagery and Execution

Published 10 Dec 2023 in cs.LG and eess.SP | (2312.05828v1)

Abstract: In the quest for efficient neural network models for neural data interpretation and user intent classification in brain-computer interfaces (BCIs), learning meaningful sparse representations of the underlying neural subspaces is crucial. The present study introduces a sparse multitask learning framework for motor imagery (MI) and motor execution (ME) tasks, inspired by the natural partitioning of associated neural subspaces observed in the human brain. Given a dual-task CNN model for MI-ME classification, we apply a saliency-based sparsification approach to prune superfluous connections and reinforce those that show high importance in both tasks. Through our approach, we seek to elucidate the distinct and common neural ensembles associated with each task, employing principled sparsification techniques to eliminate redundant connections and boost the fidelity of neural signal decoding. Our results indicate that this tailored sparsity can mitigate the overfitting problem and improve the test performance with small amount of data, suggesting a viable path forward for computationally efficient and robust BCI systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. R. M. Hardwick, S. Caspers, S. B. Eickhoff, and S. P. Swinnen, “Neural correlates of action: Comparing meta-analyses of imagery, observation, and execution,” Neurosci. Biobehav. Rev., vol. 94, pp. 31–44, 2018.
  2. X. Jiang, H. Saggar, S. I. Ryu, K. V. Shenoy, and J. C. Kao, “Structure in neural activity during observed and executed movements is shared at the neural population level, not in single neurons,” Cell Rep., vol. 32, no. 6, 2020.
  3. J. A. Gallego, M. G. Perich, L. E. Miller, and S. A. Solla, “Neural manifolds for the control of movement,” Neuron, vol. 94, no. 5, pp. 978–984, 2017.
  4. N. Padfield, J. Zabalza, H. Zhao, V. Masero, and J. Ren, “EEG-based brain-computer interfaces using motor-imagery: Techniques and challenges,” Sensors, vol. 19, no. 6, p. 1423, Jan. 2019.
  5. D.-Y. Lee, J.-H. Jeong, B.-H. Lee, and S.-W. Lee, “Motor imagery classification using inter-task transfer learning via a channel-wise variational autoencoder-based convolutional neural network,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 226–237, 2022.
  6. R. Abiri, S. Borhani, E. W. Sellers, Y. Jiang, and X. Zhao, “A comprehensive review of EEG-based brain–computer interface paradigms,” J. Neural Eng., vol. 16, no. 1, p. 011001, 2019.
  7. S.-B. Lee et al., “Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification,” Inf. Sci., vol. 502, pp. 190–200, 2019.
  8. J. Kim et al., “Abstract representations of associated emotions in the human brain,” J. Neurosci., vol. 35, no. 14, pp. 5655–5663, 2015.
  9. K.-H. Thung et al., “Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion,” Med. Image Anal., vol. 45, pp. 68–82, 2018.
  10. Y. Roy et al., “Deep learning-based electroencephalography analysis: a systematic review,” J. Neural Eng., vol. 16, no. 5, p. 051001, 2019.
  11. J.-S. Bang, M.-H. Lee, S. Fazli, C. Guan, and S.-W. Lee, “Spatio-spectral feature representation for motor imagery classification using convolutional neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 7, pp. 3038–3049, 2021.
  12. D.-Y. Kim, D.-K. Han, J.-H. Jeong, and S.-W. Lee, “EEG-based driver drowsiness classification via calibration-free framework with domain generalization,” in Proc. IEEE Int. Conf. Syst. Man, Cybern. (SMC), 2022, pp. 2293–2298.
  13. K. Yin, E. Y. Lim, and S.-W. Lee, “GITGAN: Generative inter-subject transfer for EEG motor imagery analysis,” Pattern Recognit., p. 110015, 2023.
  14. K.-T. Kim, C. Guan, and S.-W. Lee, “A subject-transfer framework based on single-trial EMG analysis using convolutional neural networks,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 1, pp. 94–103, 2019.
  15. J. H. Jeong, J. H. Cho, K. H. Shim, B. H. Kwon, B. H. Lee, D. Y. Lee, others, and S. W. Lee, “Multimodal signal dataset for 11 intuitive movement tasks from single upper extremity during multiple recording sessions,” GigaScience, vol. 9, no. 10, p. giaa098, 2020.
  16. R. Mane et al., “FBCNet: A multi-view convolutional neural network for brain-computer interface,” arXiv preprint arXiv:2104.01233, 2021.
  17. V. Sanh et al., “Multitask prompted training enables zero-shot task generalization,” arXiv preprint arXiv:2110.08207, 2021.
  18. S.-H. Lee, M. Lee, and S.-W. Lee, “Neural decoding of imagined speech and visual imagery as intuitive paradigms for BCI communication,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 12, pp. 2647–2659, 2020.
  19. S.-H. Lee, M. Lee, J.-H. Jeong, and S.-W. Lee, “Towards an EEG-based intuitive BCI communication system using imagined speech and visual imagery,” in Proc. IEEE Int. Conf. Syst. Man Cybern. (SMC), 2019, pp. 4409–4414.
  20. G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv preprint arXiv:1503.02531, 2015.
  21. H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, “Pruning filters for efficient convnets,” arXiv preprint arXiv:1608.08710, 2016.
  22. S. Srinivas, A. Subramanya, and R. Venkatesh Babu, “Training sparse neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 138–145.
  23. J. Wang, S. Zhao, C. Xu, J. Zhang, and R. Zhong, “Brain-inspired interpretable network pruning for smart vision-based defect detection equipment,” IEEE Trans. Industr. Inform., vol. 19, no. 2, pp. 1666–1673, 2022.
  24. D.-Y. Kim, D.-K. Han, and H.-B. Shin, “Calibration-free driver drowsiness classification based on manifold-level augmentation,” in Int. Winter Conf. Brain Comput. Interface (BCI), 2023, pp. 1–4.
  25. M. Lee, C.-B. Song, G.-H. Shin, and S.-W. Lee, “Possible effect of binaural beat combined with autonomous sensory meridian response for inducing sleep,” Front. Hum. Neurosci., vol. 13, pp. 425–440, 2019.
  26. E. Elsen, M. Dukhan, T. Gale, and K. Simonyan, “Fast sparse convnets,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 14 629–14 638.
  27. N. Lee, T. Ajanthan, and P. H. Torr, “SNIP: Single-shot network pruning based on connection sensitivity,” arXiv preprint arXiv:1810.02340, 2018.
  28. J. Frankle and M. Carbin, “The lottery ticket hypothesis: Finding sparse, trainable neural networks,” arXiv preprint arXiv:1803.03635, 2018.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up