谷歌用海量传感器数据训了个健康大模型 SensorFM，在 35 项任务里赢了 34 个，比传统方法靠谱多了，做可穿戴健康的朋友可以看看。
Google Research 联合 DeepMind 等团队推出 SensorFM，一个基于 ViT-1D 掩码自编码器架构的可穿戴健康基础模型。模型在超过 1 万亿分钟来自 500 万参与者的未标注传感器信号上预训练。实验对比 4 种模型规模和 4 种数据量，发现当模型容量超过数据量时性能仍可提升。使用冻结嵌入加 PCA-50 线性探针，在 35 个健康任务中的 34 个上超过了传统特征工程基线。团队还通过 agentic 教室搜索了 30,516 个预测头，并进行了临床评估以验证个人健康智能体。
Google Research Introduces SensorFM: A Wearable Health Foundation Model Pretrained on One Trillion Minutes of Sensor Data
SensorFM, a wearable health foundation model from Google Research, Google DeepMind, and university collaborators. We walk through its ViT-1D masked-autoencoder backbone, pretrained on more than one trillion minutes of unlabeled sensor signals from 5,000,000 consented participants. We examine the co-scaling results across four model sizes and four data volumes, including the case where capacity outruns data. We show how frozen embeddings plus a PCA-50 linear probe beat feature-engineered baselines on 34 of 35 tasks. We also review the agentic classroom that searched 30,516 prediction heads, and the clinician evaluation grounding a Personal Health Agent. The post Google Research Introduces SensorFM: A Wearable Health Foundation Model Pretrained on One Trillion Minutes of Sensor Data appeared first on MarkTechPost .