Models (4)
25——
Apple's foundation model trained on behavioral signals from wearables, modeling 27 HealthKit metrics to improve predictions across 57 health tasks.
Biosignals
16——
Accelerometry foundation model distilled from PPG encoders on 20M minutes of wearable data to predict health biomarkers from any motion-sensing device.
Biosignals
26—31
A self-supervised motion foundation model for wearable accelerometry, trained with relative contrastive learning on 1B segments from 87,376 participants.
Biosignals
126——
Self-supervised contrastive foundation models for wearable PPG and ECG signals, trained on ~141K Apple Watch participants from the Apple Heart and Movement Study.
Biosignals