Tag

Self Supervised Learning

All articles tagged with #self supervised learning

technology2 months ago•20 min saved

GluFormer: A universal model for decoding glucose patterns across diverse populations

Researchers introduce GluFormer, a self-supervised, autoregressive foundation model trained on over 10 million CGM measurements to learn transferable glucose representations across 19 external cohorts spanning 5 countries and multiple devices. The learned representations improve forecasting of glycemic metrics, stratify prediabetes progression better than baseline HbA1c, and identify higher long-term diabetes and cardiovascular mortality risk than HbA1c in follow-up data. A multimodal extension incorporating dietary data can simulate plausible glucose trajectories and predict individual glycemic responses to food, suggesting GluFormer as a generalizable tool to advance precision metabolic health.

via Nature|

#continuous-glucose-monitoring #foundation-model #glucose-monitoring

neuroscience2 years ago•8 min saved

Unraveling Brain Mysteries with AI's Self-Learning Models

Researchers at MIT have found evidence suggesting that the brain may use a process similar to self-supervised learning, a technique used in artificial intelligence (AI), to develop an intuitive understanding of the physical world. By training neural networks using self-supervised learning, the resulting models generated activity patterns similar to those observed in the brains of animals performing similar tasks. This breakthrough could provide insights into the inner workings of the mammalian brain and enhance our understanding of AI.

via Neuroscience News|

#ai #brain #mammalian-brain

neuroscience2 years ago•7 min saved

"Brain's Learning Process Mirrors Computational Models"

Two studies from researchers at MIT's K. Lisa Yang Integrative Computational Neuroscience Center suggest that the brain may develop an intuitive understanding of the physical world through a process similar to self-supervised learning used in computational models. The studies found that neural networks trained using self-supervised learning generated activity patterns similar to those seen in the brains of animals performing the same tasks. The findings indicate that these models can learn representations of the physical world to make accurate predictions, suggesting that the mammalian brain may use a similar strategy. The research has implications for understanding the brain and developing artificial intelligence systems that emulate natural intelligence.

via MIT News|

#brain #cognitive-functions #computational-models