NOW FOR MIND-READING ALGORITHM
at the University of Toronto Scarborough have been able to reconstruct images
of what people ‘perceive’ based on their brain activity gathered by
electroencephalography (EEG).The method, developed by Dan Nemrodov, a
postdoctoral fellowin Assistant Professor Adrian Nestor’s lab at Scarborough,
is able to digitally recreate images seen by test subjects based on EEG data.
For the study, subjects hooked up to EEG equipment were shown their facial
images while their brain activity was recorded. The activity was then used to
digitally recreate the image in the subject’s mind using a method based on
machine-learning algorithms. The method was originally pioneered by Nestor who
reconstructed facial images from functional magnetic resonance imaging (FMRI)
data in the past. However, this was the first time EEG was used. Even as EEG is
more common, portable, and inexpensive, it also has much greater temporal
resolution, measuring with great detail how a percept develops in time right
down to milliseconds.