Meta releases new AI model capable of predicting human brain activity

According to the company, the system acts as a “digital twin” of neural activity, allowing researchers to predict brain responses with high speed and precision. The model was trained on functional MRI (fMRI) data collected from more than 700 volunteers exposed to a wide range of media, including videos, podcasts and text.

“We’re introducing TRIBE v2, our next-gen model that acts as a ‘digital twin of human neural activity’. This offers unprecedented speed, accuracy, and a 70x resolution increase as compared to similar models to predict how the brain responds to almost any sight or sound — enabling neuroscientists and clinical researchers to test theories without requiring human subjects,” the statement reads.

Meta says the model can make so-called “zero-shot” predictions, meaning it can generalise its results to new users, languages and tasks without additional training.

“TRIBE v2 reliably predicts high-resolution fMRI brain activity — enabling zero-shot predictions for new subjects, languages, and tasks — and consistently outperforms standard modeling approaches. By creating a digital model of the human brain, researchers can rapidly test hypotheses about its underlying functions without the need for human subjects in every experiment,” the company added.

The company also released the model’s code, research paper and an interactive demo under a non-commercial license to support further research.

“By sharing this work, we hope to help accelerate neuroscience research that will unlock scientific and clinical breakthroughs for the greater good,” Meta said.

Earlier, China approved a brain implant designed to help people with severe paralysis regain hand movement.