The researchers call this method neuroadaptive generative modelling
Researchers at the University of Helsinki have developed a new computer that can monitor brain activity and present what the user is thinking of in images, the Independent reported.
Previous brain-computer interfaces have allowed the subject to use their brain to spell out individual letters or move a cursor. But in this case, the interaction is between the subject’s brain and the AI generated the images.
The researchers call this method neuroadaptive generative modelling.
The neural network was then able to adapt its prediction of what face the person was thinking of, and generate images accordingly.
Eventually, the images generated by the computer progressively matched those thought of by the participants, with an accuracy of 83%.
The study was published in the journal Scientific Reports this month.
“The technique combines natural human responses with the computer's ability to create new information. In the experiment, the participants were only asked to look at the computer-generated images,” Tuukka Ruotsalo, a researcher at the University of Helsinki and a professor at University of Copenhagen, said in a statement.
“The computer, in turn, modelled the images displayed and the human reaction toward the images by using human brain responses. From this, the computer can create an entirely new image that matches the user's intention.”
The researchers also believe that this development could be used to help creatives, as well as getting a better understanding of how people perceive things.