MuBiNN: Multi-Level Binarized Recurrent Neural Network for EEG signal Classification

@article{Mirsalari2020MuBiNNMB,
  title={MuBiNN: Multi-Level Binarized Recurrent Neural Network for EEG signal Classification},
  author={Seyed Ahmad Mirsalari and S. Sinaei and M. Salehi and M. Daneshtalab},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.08914}
}
  • Seyed Ahmad Mirsalari, S. Sinaei, +1 author M. Daneshtalab
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Recurrent Neural Networks (RNN) are widely used for learning sequences in applications such as EEG classification. Complex RNNs could be hardly deployed on wearable devices due to their computation and memory-intensive processing patterns. Generally, reduction in precision leads much more efficiency and binarized RNNs are introduced as energy-efficient solutions. However, naive binarization methods lead to significant accuracy loss in EEG classification. In this paper, we propose a multi-level… CONTINUE READING

    Figures, Tables, and Topics from this paper

    References

    SHOWING 1-10 OF 43 REFERENCES
    Multi-level Binarized LSTM in EEG Classification for Wearable Devices
    • 3
    • PDF
    Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals
    • 533
    • PDF
    EEG signal classification using PCA, ICA, LDA and support vector machines
    • 729
    • PDF
    Survey on EEG Signal Processing Methods
    • 51
    Loss-aware Binarization of Deep Networks
    • 122
    • PDF
    Alternating Multi-bit Quantization for Recurrent Neural Networks
    • 69
    • PDF
    LSTM: A Search Space Odyssey
    • 2,406
    • PDF