AI Generative Adversarial Network Attractive Face
We have seen the future of dating apps, and they’ll all be AI-powered. Why? Researchers used electroencephalography (EEG) measurements to identify what kind of facial features people found to be attractive, and then uploaded the data to an artificial intelligence program, or a generative adversarial neural network (GAN). This program then familiarized itself with the types of faces individual people found desirable, and then synthesized new ones tailored exactly to their preferences. Read more for a video and additional information.



The new AI-generated faces were then shown to the 30 volunteers alongside multiple additional faces, which were rated by participants as attractive 80 percent of the time, compared to just 20 percent for the randomized faces. How would this work in let’s say a dating app? Well, AI would first show new users a series of AI-generated faces and then compare them to what is already in their database.

Acer Nitro 5 Gaming Laptop, 10th Gen Intel Core i5-10300H,NVIDIA GeForce GTX 1650 Ti, 15.6" Full HD IPS 144Hz Display, 8GB DDR4,256GB NVMe SSD,WiFi 6, DTS X Ultra,Backlit Keyboard,AN515-55-59KS
  • 10th Generation Intel Core i5-10300H Processor (Up to 4.5GHz)
  • 15" Full HD Widescreen IPS LED-backlit 144Hz Refresh Display | NVIDIA GeForce GTX 1650 Ti Graphics with 4 GB of dedicated GDDR6 VRAM
  • 8GB DDR4 2933MHz Memory | 256GB NVMe SSD (2 x PCIe M.2 Slots - 1 Slot Open for Easy Upgrades) & 1 - Available Hard Drive Bay
  • LAN: Killer Ethernet E2600 10/100/1000 Gigabit Ethernet LAN | Wireless: Intel Wireless Wi-Fi 6 AX201 802.11ax
  • Backlit Keyboard | Acer CoolBoost Technology with Twin Fans and Quad Exhaust Ports Design

They did not have to do anything but look at the images. We measured their immediate brain response to the images. Succeeding in assessing attractiveness is especially significant, as this is such a poignant, psychological property of the stimuli,” said cognitive neuroscientist Michiel Spape.