Scientists in Japan used AI to identify categories of images in dreams
A research study in Japan monitored participants' brains with scanners while they slept and woke them during early sleep phases to describe what they had just dreamed. Using artificial intelligence algorithms, the scientists compared those accounts with the brain recordings and identified patterns linked to categories of images such as people, buildings, vehicles and furniture. The system predicted with significant accuracy the type of image associated with brain activity, though it did not allow dreams to be visualized like a film.
In 40 seconds
- Participants slept with brain scanners and were woken to describe what they had dreamed seconds earlier.
- AI algorithms linked brain signals to categories such as people, buildings, vehicles and furniture.
- The system predicted the type of image but did not reconstruct complete scenes or generate video of dreams.
IASummary generated by artificial intelligence from a story by Portafolio. It may contain errors: the original source prevails.



Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.