Developers from Purdue University have created a neural network that can analyze fMRI shots of the brain made while watching a video, and then in real time determine what the person was looking at.
The experiment involved three subjects, who were shown about a thousand small videos. During the show, scientists were able to obtain a huge amount of fMRI data, which then began to demonstrate a convolutional neural network, trained to compare brain activity with video clips. According to the picture fMRI, the network has learned very quickly and correctly to determine what exactly the volunteer looked at the time the picture was taken.
In addition, the neural network learned to decipher the data of other people, based on the information received from the fMRI of other volunteers of information, with the result being equally high as for the fMRT data of healthy subjects and those with visual defects.
Thanks to this research, scientists were able to decipher the thoughts, and at the same time found out which parts of the brain are responsible for recognizing images and video clips. The fact is that the brain divides the video into separate components. For example, if a person sees a car moving in the background of the wall, then one area of the brain recognizes the wall, and the other car - so scientists can trace the brain's work by comparing individual blocks of information and bringing it together into a single picture.
The article is based on materials .
Comments
Post a Comment