Researchers have paired artificial intelligence and brain activity data to generate personally attractive images
Like it or not, artificial intelligence is on its way to changing virtually every facet of our lives. Hyperreal humanoids are already creating art that’s indistinguishable from the human variety, and AI-powered technology is well on its way to revolutionising the fashion and fragrance industries. Now, it also looks set to infiltrate the world of dating (or at least help you to find someone hot to date in the first place).
More specifically, researchers from the University of Helsinki and the University of Copenhagen have managed to teach AI what faces an individual person finds attractive, and how to generate artificial portraits in response.
The study, titled “Brain-computer interface for generating personally attractive images”, involved taking 30 volunteers and monitoring the electrical activity in their brain, while they looked at artificial portraits created by a generative adversarial network (GAN), pulled together from thousands of images of real celebrities.
“It worked a bit like the dating app Tinder,” explains Michiel Spapé, a senior researcher at the University of Helsinki, via Neuroscience News. “The participants ‘swiped right’ when coming across an attractive face. Here, however, they did not have to do anything but look at the images. We measured their immediate brain response to the images.”
The data from the readings was then analysed using machine learning techniques, generating a network that helped create new portraits based on a person’s individual preferences.
“By interpreting their views, the AI model interpreting brain responses and the generative neural network modelling the face images can together produce an entirely new face image by combining what a particular person finds attractive,” says Academy Research Fellow and Associate Professor Tuukka Ruotsalo, who led the project. The new images were found to match the subjects’ preferences with an accuracy of 80 per cent.
Does this mean that the dating apps of the near future are going to get a whole lot more efficient? Well, maybe. But the study also has potential to expose unconscious biases and stereotypes, Spapé adds, saying: “Potentially, we might gear the device towards identifying stereotypes or implicit bias and better understand individual differences.”
Disturbingly narrow beauty ideals being uncovered by artificial intelligence is nothing new. In 2016, the deep learning group Youth Laboratories launched a contest judged solely by robots, Beauty.AI. Of 7,000 entrants, 44 were selected as winners, and only one was dark-skinned. Youth Laboratories now operates Diversity.AI, a think tank that’s devoted to addressing algorithmic bias.
Spapé also notes that attractiveness is a more challenging subject than defining concrete physical traits, “as it is associated with cultural and psychological factors that likely play unconscious roles in our individual preferences. Indeed, we often find it very hard to explain what it is exactly that makes something, or someone, beautiful: Beauty is in the eye of the beholder.”