They say beauty lies in the eye of the beholder, but it’s actually much deeper than that.
The concept of physical beauty lies in the mind, defined by the features we find attractive in other people’s faces. These subtle preferences represent some of our most private inner thoughts, but that doesn’t mean they can’t be controlled or even predicted.
In a new study, researchers used electroencephalography (EEG) measures to identify what types of facial features seemed attractive to people, and then fed the results to an artificial intelligence (AI) program.
The machine learning system, called a generative adversarial neural network (GAN), was able to first become familiar with what types of faces people found desirable and then fabricated completely new ones designed specifically for like: personalized visions of synthesized beauty, as unattainable. as they were perfect.
The experiment, led by a team of psychologists and computer scientists from the University of Helsinki in Finland, was a kind of massive Tinder session for the 30 volunteers who participated.
Except for some big differences.
While participants sat in front of a computer screen showing them a series of faces, none of the faces shown were real people, but were realistic-looking artificial portraits generated from a set of data. about 200,000 images of famous people.
Unlike the usual use of Tinder, participants also wore elastic caps fitted with electrodes designed to measure their brain activity while looking at their faces. Nor did they have to slide to the right when they saw someone who liked the look, all this was taken care of.
“They had to do nothing but look at the pictures,” explains cognitive neuroscientist Michiel Spapé. “We measured their immediate brain response to the images.”
These individual measurements of neuronal activity were evaluated by the GAN, which was able to interpret brain responses based on the attractiveness that the viewer considered each artificial face.
Using this data, the GAN was able to generate new faces reported by people’s EEG attraction identifiers.
In a second experiment, these newly invented faces were shown back to the volunteers, who rated them in terms of attractiveness, along with other randomly generated face images.
Ultimately, the results validated the researchers ’test, with participants rating the adapted images to be attractive in approximately 80% of cases, while the other faces were only selected 20% of the time.
While this is just a small study, it is just one more example of how intelligent AI systems are becoming their understanding of what makes us mark, even intimate and often unexpressed notions, such as mastery of personal attraction.
“Being successful in assessing attractiveness is especially significant, as it is a psychological and poignant property of stimuli,” Spapé says.
“If this is possible in something as personal and subjective as attractiveness, we can also examine other cognitive functions such as perception and decision making. Potentially, we could target the device to identify implicit stereotypes or biases and better understand individual differences. “.
The findings are reported in IEEE transactions in affective computing.