These are all faces made by NIVIDIA’s neuro-network, none of them are real.
They have been synthesized by Nvidia’s new AI algorithm, a generative adversarial network capable of automagically creating humans, cats, and even cars.
To be more precise, these faces are created by a generative adversarial network (GAN) developed by Nvidia, using deep learning techniques to produce realistic portraits out of a database of existing photos.
With a GAN, two neural networks – neural as in designed to mimic the brain’s decision-making process – work in tandem. Here, one network generates a fake face, while another decides if it’s realistic enough by comparing it with photos of actual people.
If the test isn’t passed, the face generator tries again.