Mind-reading AI turns thoughts into pictures with amazing accuracy

Researchers have achieved a significant breakthrough in the field of neuroscience and artificial intelligence (AI) by successfully reconstructing images from brain activity.

By employing an improved mind-reading AI system, they could produce “closest” reconstructions of images, particularly when using direct recordings of brain activity.

This remarkable feat was accomplished by scientists at Radboud University in the Netherlands. They have clubbed their previous study with the latest research to generate accurate reconstructions.

“As far as I know, these are the closest, most accurate reconstructions,” said Umut Güçlü, a member of the research team.

This mind-reading technology development has the potential to pave the way for new treatments for vision loss.

Two studies for deeper understanding

The team conducted two different studies. In the first study, they placed a few volunteers inside a functional magnetic resonance imaging (fMRI) machine. This machine measures changes in blood flow in the brain, which can be used to understand brain activity.

The volunteers were shown pictures of faces, and the fMRI captured the neural activity in their visual cortex, which was then fed into the AI algorithm. The AI was able to reconstruct the images that closely resembled the original pictures.

The second study involved reanalyzing data from previous experiments where electrode arrays were implanted in a macaque monkey’s brain to record its activity as it looked at AI-generated images.

This time, the improved AI was able to reconstruct the original images with near-perfect accuracy. The images created from the monkey’s brain activity were almost identical to the original images.

This is because the implanted devices provided precise data on the monkey’s brain activity.

The researchers then used a sophisticated AI system to analyze the brain activity data from both experiments. This AI system was unique because it could learn which parts of the brain to focus on.

By doing so, it was able to create images that were very similar to the original images seen by the volunteers and the monkey. “Basically, the AI is learning when interpreting the brain signals where it should direct its attention,” says Güçlü.

Wide range of applications

The applications of this technology span various fields. In the medical field, it could potentially restore vision by stimulating the brain to create richer visual experiences for individuals with visual impairments.

Moreover, it has the potential to revolutionize communication for individuals with disabilities by providing novel avenues for interaction and expression.

“Considering the speed of progress in the field of generative modeling, we believe that this framework will likely result in even more impressive reconstructions of perception and possibly even imagery in the near future,” concluded the researchers’ study.