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

arXiv: https://arxiv.org/abs/2004.08914 · HTML: https://mlsanity.com/paper/2004.08914/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 1 of 1)

- [Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices](https://mlsanity.com/paper/2607.18149/) (2026)

## Abstract (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 binarized LSTM, which significantly reduces computations whereas ensuring an accuracy pretty close to the full precision LSTM. Our method reduces the delay of the 3-bit LSTM cell operation 47* with less than 0.01% accuracy loss.