Skip to content

Dataset · brain-bzh

Open part of EEG recording corpus for REVE model

brain-bzh/reve-dataset

About 4.85 TB of electroencephalogram recordings under open licenses for training neural networks on brain signals.

What's inside

This is the open portion of the dataset used to pre-train the REVE (Representation Learning for EEG) model. It contains approximately 4.85 TB of raw and processed electroencephalogram (EEG) recordings distributed under open licenses. The set is designed for time series forecasting, feature extraction, and fill-mask tasks.

What you can do with it

  • Pre-training foundational models for biomedical signal analysis and neurointerfaces
  • Feature extraction from EEG for medical diagnostics
  • Training multi-channel time series forecasting models
Tasks
Fill mask, Embeddings, Time series forecasting
Downloads this month
3.5K
Likes
9

How to load it

from datasets import load_dataset

ds = load_dataset("brain-bzh/reve-dataset")