AI_System_Translates_Brain_Activity_into_Text_for_Noninvasive_Communication_#shortsvideo_#facts(720p)

  • last year
Researchers at The University of Texas at Austin have developed a new artificial intelligence system called a semantic decoder that can translate a person's brain activity into text without the need for surgical implants. Based on a transformer model similar to ChatGPT and Bard, the system could help individuals who are mentally conscious but physically unable to speak, such as stroke patients, communicate again. The decoder was trained using podcasts listened to by participants in an fMRI scanner and can generate corresponding text from brain activity alone. While imperfect, the system can capture the overall meaning of what is being said or thought for an extended period of time. The researchers addressed potential concerns about misuse, emphasizing that the system only works with cooperative participants who willingly trained the decoder. Though not yet practical for use outside the laboratory, the technology could potentially be adapted for use with other brain-imaging systems.

Recommended