Singaporean researchers have created an advanced AI system that can analyze brain wave patterns and create pictures of what a person is observing.
The team of scientists is gathering brain scan data from approximately 58 volunteers. These participants are shown anywhere from 1,200 to 5,000 various pictures, including animals, food, structures, and human actions, while undergoing an MRI scan.
In a span of nine seconds each, with pauses in-between, the AI system, known as MinD-Vis, correlates the brain scans with the images. This process results in the creation of a distinct AI model for every participant.
These models empower computers to interpret thoughts and replicate the visuals that an individual is observing.
MinD-Vis understands your brain activities just like ChatGPT
Similar to how ChatGPT understands human languages, this system understands your brain actions, explained Jiaxin Qing, a Ph.D. student and one of the main researchers at The Chinese University of Hong Kong (CUHK IE).
It then converts these brain activities into a language that Stable Diffusion, an open-source AI capable of generating images from text, can grasp, Qing further expressed.
Qing pointed out that the decoded pictures consistently resembled what the participants had viewed.
Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
abs: https://t.co/C6Dq7bX9VK
project page: https://t.co/6nTi6yb8xN
github: https://t.co/mnfKG8Nhj2 pic.twitter.com/DSxii6Exim— AK (@_akhaliq) November 15, 2022
Li Ruilin, one of the participants, is deeply intrigued by brain decoding.
“This brain decoding like using brain signals to generate the natural modalities is very interesting and exciting work,” said Ruilin. “I’m also interested in what happened in my brain and what my brain can output and what I’m thinking.”
The research team believes that this technology holds the potential to assist individuals in the future.
Chen Zijiao, from the National University of Singapore’s School of Medicine, explained that “for some patients without motor ability…maybe we can help him to control their robots [artificial limbs…or] communicate with others…just using their thoughts instead of speech if that person couldn’t speak at that time.”
Chen also highlighted the possibility of evolving this technology to seamlessly merge with virtual reality headsets. This way, users could navigate the metaverse using their thoughts instead of relying on physical controllers.
‘This is going to be very, very difficult’
The researchers attribute the creation of their mind-reading AI to the increased accessibility of MRI datasets and the recent progress in computational power, which enables efficient data processing.
#Watch | Researchers from National University of #Singapore say they've developed MinD-VIS, a mind-reading #AI. The tech can 'read' a person's thoughts & re-create visuals s/he is examining. However, there are possible risks lurking & relative lack of #legislation in AI research pic.twitter.com/tbVCglTPkR
— CNBC-TV18 (@CNBCTV18News) August 16, 2023
Nevertheless, the team acknowledges that it will require many years of further advancements for MinD-Vis to accurately decipher the general public’s thoughts.
“We are trying to test the possibility right now, but I will say in terms of the dataset that is available right now, the computational power we have, as well as the huge heterogeneity or inter-individual differences in our brain anatomy as well as brain function; this is going to be very, very difficult,” said Juan Helen Zhou, an associate professor at the National University of Singapore.
See all the latest news from Greece and the world at Greekreporter.com. Contact our newsroom to report an update or send your story, photos and videos. Follow GR on Google News and subscribe here to our daily email!
