BENDR: Using Transformers and a Contrastive Self-Supervised Learning Task to Learn From Massive Amounts of EEG Data
By Demetres Kostas, Stephane T Aroca-Ouellette, Frank Rudzicz. Frontiers in Human Neuroscience, 2021
368 citations recorded by the source corpus.
Deep neural networks (DNNs) used for brain–computer interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts. While some success is found in such an approach, we suggest that this interpretation is limited and an alternative would better leverage the newly (publicly) available massive electroencephalography (EEG) datasets. We consider how to adapt techniques and architectures used for language modeling (LM) that appear capable of ingesting awesome amounts of data toward the development of encephalography modeling with DNNs in the same vein. We specifically adapt an approach effectively used for automatic speech recognition, which similarly (to LMs) uses a self-supervised training objective to learn compressed representations of raw data signals. After adaptation to EEG, we find that a single pre-trained model is capable of modeling completely novel raw EEG sequences recorded with differing hardware, and different subjects performing different tasks. Furthermore, both the internal representations of this model and the entire architecture can be fine-tuned to a variety of downstream BCI and EEG classification tasks, outperforming prior work in more task-specific (sleep stage classification) self-supervision.
Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/c008f0f47bde9c224d5cdbc63988033995fa87c4
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Xiaorong Gao
- Qingqing Zheng
- Bingchuan Liu
- Yonghao Song
- Shangkai Gao
- Tzyy-Ping Jung
- Xiaogang Chen
- Masaki Nakanishi
In Electrical and Electronic Engineering
Citations in the corpus
- EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization (2022, methodology): “Kostas et al. [34] designed a pre-training and fine-tuning approach using Transformer for EEG classification tasks.”
- Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI (2024, background): “BENDR (Kostas et al., 2021) adapted Wav2vec 2.0 (Baevski et al., 2020), which uses contrastive learning to learn compressed representations of raw EEG signals.”
- Nanomedicine-Driven Modulation of the Gut–Brain Axis: Innovative Approaches to Managing Chronic Inflammation in Alzheimer’s and Parkinson’s Disease (2025, unknown): “Applications of SSL in medical imaging, electronic health records, and RNA/DNA networks suggest its potential in expo-some research, particularly when large datasets become available [299–303].”