metaai·lightalo unofficial · independent
Universe / AI for Science / Brain & AI: Decoding Perception from MEG/EEG
AI for Science · 2022-2023

Brain & AI: Decoding Perception from MEG/EEG

Reconstructing what you see from brain signals

open source

Latest: Image decoding from MEG (October 2023); speech-perception decoding (2022 preprint, published 2023)

FAIR's neuroscience program showed that self-supervised AI models align with brain activity — and can decode it. A 2023 Nature Machine Intelligence paper decoded perceived speech from non-invasive MEG/EEG using wav2vec 2.0-style contrastive learning; a companion 2023 system reconstructed seen images from MEG signals in near real time using DINOv2 embeddings.

Why it matters

Showed self-supervised AI representations align with brain activity well enough to decode it: contrastive learning between wav2vec 2.0 speech embeddings and MEG/EEG identified perceived speech, and DINOv2 embeddings reconstructed seen images from MEG in near real time. Code covering 175 volunteers and 160+ hours of recordings is open.

Facts

Try it yourself

Lineage

Led toBrain2Qwerty

See the whole family tree →

Sources

More in AI for Science

OpenDAC / ODAC25Open Catalyst ProjectOpen Materials 2024fairchemESM / ESMFoldOpen Molecules 2025

Read the AI for Science story on the sky →

✦ Open on the map Explore AI for Science Quiz me