AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

BIOT: Biosignal Transformer for Cross-data Learning in the Wild

Chaoqi Yang, M Brandon Westover, Jimeng Sun

NeurIPS 2023 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and circuits · 45 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add unsupervised pre-training on PREST (ablation)BIOT · CHB-MITBalanced Acc.: 0.6640 -> 0.6942Improved
add unsupervised pre-training on PREST (ablation)BIOT · TUEVBalanced Acc.: 0.4682 -> 0.5207Improved
add unsupervised pre-training on PREST (ablation)BIOT · TUABBalanced Acc.: 0.7925 -> 0.7907No clear effect
add PREST+SHHS joint pre-training (ablation)BIOT · TUABBalanced Acc.: 0.7925 -> 0.8019Improved
add PREST+SHHS joint pre-training (ablation)BIOT · IIIC SeizureBalanced Acc.: 0.5762 -> 0.5800Improved
add ECG pre-training on Cardiology with 12 leads (ablation)BIOT · PTB-XLBalanced Acc.: 0.8315 -> 0.8421Improved
pretrain with 12 leads instead of 6 leads (ablation)BIOT Cardiology · PTB-XLBalanced Acc.: 0.8350 -> 0.8421Improved
supervised pre-training on IIIC Seizure (16ch, 10s) (ablation)BIOT · TUEVCohen's Kappa: 0.4482 -> 0.5316Improved
supervised pre-training on CHB-MIT (8ch, 10s) (ablation)BIOT · TUEVBalanced Acc.: 0.4682 -> 0.4123Hurt
use 16 channels and 10s instead of 5s or 8 channels in supervised pretraining (ablation)BIOT on TUAB pretrain · TUEVBalanced Acc.: 0.4954 -> 0.5256Improved
pre-train on all six EEG datasets vs PREST+SHHS (ablation)BIOT · IIIC SeizureWeighted F1: 0.5878 -> 0.5737Mixed
pre-training with linear-attention BIOT vs scratch under missing channels/segments (ablation)BIOT · TUEV, IIIC SeizureKappa/Weighted F1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy