Scientists at the University of Texas at Austin developed an artificial intelligence system that can translate human brain activity into continuous text. Published in the journal Nature Neuroscience in May 2023, the study was led by neuroscientist Alexander Huth and computer scientist Jerry Tang.
Volunteers listened to narrative stories for over sixteen hours while resting inside a functional magnetic resonance imaging scanner. The researchers trained a custom artificial intelligence model based on GPT technology to match precise blood flow changes in the brain with specific words and meanings.
Unlike older experimental brain implants, this breakthrough requires no surgery. When subjects listened to new stories or silently imagined speaking a tale, the decoder generated text capturing the core meaning of their private thoughts.
The researchers emphasized that the decoder currently requires extensive individual cooperation and cannot function without customized training. Even so, the breakthrough offers real hope for paralyzed patients who have lost their ability to speak.
#neuroscience #artificialintelligence #brainresearch #biotechnology #sciencefacts #techinnovation #futuretech
Disclaimer: This video is for informational and educational purposes. Content is based on published scientific studies and visual media illustrates the concepts.
