Creating images based on a slogan, answering a question or correcting a document are some of the things that can be done artificial intelligence. However, researchers are using this technology to revolutionize science and medicine in ways that seemed like science fiction just a decade ago.
A new artificial intelligence system created by neuroscientists at the University of Texas aims to decode data from brain scans and transcribe it into coherent text.
Artificial intelligence expert recommends using watermarks in images and texts created by AI
By means of a chip implanted in the brains of a group of participants, the Texas scientific team succeeded transcribe sentences by analyzing magnetic resonance imaging brain recordings. These brain recordings record what a subject imagines, thinks, hears or says.
continuously #language from which to decode #fMRI recordings to recover the meaning of perceived and imagined speech stimuli and of silent video clips
New from @jerryptang @Alexander et al. https://t.co/rwstpfoYUW
—Nature Neuroscience (@NatureNeuro) May 1, 2023
In the study, the research team found that the artificial intelligence decoder can be trained to reconstruct the continuous language. The trial involved three participants, who were implanted with a chip and then asked to watch silent movies and create dialogues and stories.
The researchers’ decoder managed to use their brain activity to write sentences. One subject thought, “I don’t have my driver’s license yet,” and the decoder predicted, “He hasn’t even started learning to drive yet.”
Artificial intelligence company is already developing a new wearable device without a screen
According to the abstract of the study, led by Alexander Huth, this decoder generates comprehensible word sequences that recover meaning from observed speech, imagined speech and even silent videos, demonstrating that a single decoder can be applied to a variety of tasks.
Due to the nature of the study, the ethical question about the privacy of thoughtssomething that scientists also put into practice.
“Because brain-computer interfaces must respect mental privacy, we tested whether successful decoding requires collaboration between subjects and we found that the subject’s cooperation is required for both training and application of the decoder.call the researchers.
Source: Eluniverso
Mabel is a talented author and journalist with a passion for all things technology. As an experienced writer for the 247 News Agency, she has established a reputation for her in-depth reporting and expert analysis on the latest developments in the tech industry.
