← Back to all news
arXiv Machine Learning By Kleanthis Avramidis, Ivan Tashev, Dimitra Emmanouilidou

BrainCodes: A Lightweight EEG Foundation Model over Discrete Neural Codes

Read the original on arXiv Machine Learning →

BrainCodes is a lightweight EEG foundation model that uses a quantization-based neural tokenizer and a spatiotemporal encoder to learn transferable EEG features from over 800 hours of data across more than 1,000 participants. The model is pretrained with a self‑supervised objective that encourages spatial connectivity and sensitivity to narrowband neural oscillations, enabling it to match or surpass state‑of‑the‑art performance on tasks such as sleep staging, attention assessment, and cognitive load estimation. It achieves these results while using up to 97% fewer trainable parameters, making it suitable for low‑resource wearable devices, and its evaluation framework analyzes the geometry and invariances of the learned representations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 14

BRIDGE-EEG: Bridging Self-Supervised Pretraining and Efficient Deployment for Cross-Dataset EEG Classification

BRIDGE-EEG is an efficient multi‑task EEG classification pipeline that leverages self‑supervised pretraining while dramatically reducing model size. It maps heterogeneous EEG recordings to a unified 62‑channel time‑frequency representation, pretrains an SE‑ResNet18 teacher with SimCLR, and distills it into smaller SE‑ResNet8 and SE‑ResNet4 students. The compact models achieve accuracy comparable to or better than larger foundation models on abnormality detection and emotion recognition, and they consume up to three times less energy on edge devices, enabling deployment on wearable hardware.

By Meghna Roy Chowdhury, Chengwei Zhou, Haotian Yu, Gourav Datta, Shreyas Sen
efficiencybenchmarks
More like this →
arXiv Machine Learning
Aug 4

SingLEM: Single-Channel Large EEG Model

arXiv:2509. 17920v2 Announce Type: replace Abstract: Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability.

By Jamiyan Sukhbaatar, Satoshi Imamura, Ibuki Inoue, Shoya Murakami, Kazi Mahmudul Hassan, Seungwoo Han, Ingon Chanpornpakdi, Toshihisa Tanaka
llms
More like this →