Meta has developed an artificially intelligent (AI) system that can scan a human brain and quickly replicate the images that a person is thinking about — in a matter of milliseconds.
Facebook and Instagram parent company Meta unveiled the groundbreaking AI mind-reading technology that can instantaneously decode visual representations in the brain into real images.
In a new paper titled “Brain Decoding: Towards a Real-Time Decoding of Images from Brain Activity,” Meta’s team outlines how the AI system can replicate images with millisecond precision through a non-invasive neuroimaging technique in which thousands of brain activity measurements are captured.
The AI system is capable of decoding visual representations in the brain using magnetoencephalography (MEG) signals. MEG is a non-invasive neuroimaging technique that measures the magnetic fields produced by neuronal activity in the brain.
“Using magnetoencephalography (MEG) we showcase an AI system capable of decoding the unfolding of visual representations in the brain with an unprecedented temporal resolution,” the Meta researchers say.
The researchers used deep learning models to align MEG signals with pre-trained representations of images, allowing them to identify matching images from brain activity. The resulting process enables images to be reconstructed from the MEG signals by feeding them into AI generative models.
“Overall, these results provide an important step towards the decoding—in real time—of the visual processes continuously unfolding within the human brain,” Meta’s research team states in the paper.
The images that the AI system produces are not perfect replications. However, the reconstructed images do preserve many of the original features, such as object categories even if the generated images are not completely accurate.
Furthermore, according to AI Business, Meta’s researchers achieved their main goal — to generate a continuous flow of images decoded from brain activity in real-time.
AI Business reports that researchers believe that the AI system could be beneficial in the medical field especially where specific individuals have lost the ability to verbally communicate.
It could be used to assist patients whose brain lesions make it a challenge to communicate — something that requires greater speed than an fMRI-based system could produce.
“The present effort thus paves the way to achieve this long-awaited goal,” the paper reads.
Image credits: All photos via Meta.