Researchers at the University of Texas have developed a system of artificial intelligence non-invasive focused on translating a person’s brain activity into conversations. According to the study published in the journal Natural neurosciencethe system, called semantic decoder, may benefit patients who have lost the ability to physically communicate after suffering a stroke, paralysis or other degenerative diseases.

According CNBC, the system uses a transformer model, similar to those supported by Google’s Bard and OpenAI’s ChatGPT chatbots.

• Why scientists fear a catastrophic future caused by artificial intelligence
• European Union expects agreement this year on AI law

In the study, participants trained the decoder by listening to several hours of podcasts on an fMRI scanner, which is a large machine that measures brain activity. The system does not require surgical implants.

Once the AI ​​is trained, it can generate a stream of text as the participant listens to a conversation or imagines telling a new story. The resulting text is not an exact transcription, but the researchers crafted it with the intention of capturing general thoughts or ideas.

According to a press release, the AI ​​produces text that closely or precisely matches the intended meaning of the participant’s original words about half the time.

For example, when a participant heard the words “I still don’t have my driver’s license” during an experiment, the thoughts translated to “She hasn’t even started learning to drive yet.”

“For a non-invasive method, this is a real leap forward from what has been done before, which are usually single words or short sentences,” said Alexander Huth, one of the managers. of the study. “We get the model to decode continuous language over long periods of time with complicated ideas.”

At this time, the decoder cannot be used outside of a lab environment as it relies on the fMRI scanner. But researchers believe that eventually AI could be used through more portable systems.

You want to discover the exclusive content of WORK TIME? Access the digital version