“Third Thumb” Augmentation Changes the Way we Think of Prosthetics
There’s nothing more popular in the science and technology world today than artificial intelligence (AI). With companies like Google now pushing an “AI-first” policy, not to mention AlphaGo’s show of dominance against the best Go players we humans could come up with, it’s pretty clear that AI is here to stay – and rise. Which is why, when a Google employee says he developed a program that allows an AI to create realistic human faces from scratch, it’s best you give him a listen.
Biophysicist Dr. Mike Tyka recently revealed on his blog that he’s been experimenting with generative adversarial networks (GANs) in order to generate portraits of various different human faces. Unlike previous methods that used convolutional neural networks, like DeepDream, Tyka relied on algorithms used in unsupervised machine learning. By having a detailed understanding of what a face is, what makes up a face, and where each feature is placed, the network then begins generating images that look not too dissimilar from an actual human face.
Below are several images which Tyka was able to generate using GANs (if you’d like to see more, click here):
Photo(s) Credit: Mike Tyka
“For a while now I’ve been experimenting with ways to use generative neural nets to make portraits. Early experiments were based on deepdream-like approaches using backprop to the image but lately I’ve focused on GANs.”
– Mike Tyka
The images produced using GANs are quite astonishing, though shouldn’t be all that surprising. Previous studies on GANs have shown similar results, whereby “generated images are of high quality as confirmed by a visual Turing test,” generating “samples that humans cannot distinguish from real data.” Thus giving AI the power to see and understand the intricate details of our own phenotypical attributes.
And this won’t be the last that we see GANs being used to help generate even more complex images using data from the physical world. As research continues, the power of AI to conceptualize and produce realistic results of how it perceives our world will make the images shown above look like chicken scratch. What a time to be alive!
About the author
B.J. Murphy is the Editor and Social Media Manager of Serious Wonder. He is a futurist, philosopher, activist, author and poet. B.J. is an Affiliate Scholar for the Institute for Ethics and Emerging Technologies (IEET) and an Ambassador for the robotics company Humai.
You may also like
