META has developed AI for “reading thoughts”

META has published a study on the “brain decoder”, which, using artificial intelligence, transforms thoughts into speech.

According to researchers, the accuracy of the algorithm reached 73% when using a set of 793 words often used in everyday life.

Scientists believe that their development will help not only millions of people who have lost the opportunity to speak and write, but also in studying the human brain.

In the future, researchers plan to increase the initial dictionary of the algorithm so that it can more accurately determine the words.

Recall that in August Meta introduced a chatbot from 175 billion parameters. Less than a week after the release of the virtual interlocutor was convicted of anti -Semitism and discontent Facebook.

In July, researchers from META developed a joint-algorithm SPhere to verify the facts in Wikipedia.

In the same month, the technical gigant presented the artificial intelligence model NLLB-200 for online https://gagarin.news/ua/news/the-bitcoin-community-celebrates-pizza-day/ translators. The algorithm supports 200 languages, including unexpressed.

Subscribe to FORKLOG news at Telegram: Forklog AI – all news from the world of AI!