MIT researchers developed an algorithm trained to generate horrifying images in an attempt to find the scariest faces and locations possible, and then rely on humans to see which approach makes the freakiest images.
Using TITAN X GPUs and cuDNN to train their deep learning models, the researchers used the infamous style transfer technique and generative adversarial networks to curate the ghoulish images.
“We use state-of-the-art deep learning algorithms to learn what haunted houses, ghost towns or toxic cities look like,” said MIT Media Lab researcher Pinar Yanardag Delul. The algorithm extracts elements — such as a bruised-black palette — from scary templates and implants them in the landmarks.
The researchers also used Google’s DeepDream method to develop ghastly portraits and voters can rate the images on the Nightmare Machine website to teach the system to make images even scarier.
Read more >
AI-Powered ‘Nightmare Machine’ Generates Horrifying Images
Oct 27, 2016
Discuss (0)
AI-Generated Summary
- Researchers at MIT developed an algorithm to generate frightening images using deep learning models trained on TITAN X GPUs and cuDNN.
- The algorithm uses style transfer and generative adversarial networks to create scary images by extracting elements from frightening templates and combining them with landmarks.
- Users can rate the generated images on the Nightmare Machine website, helping the system to improve and create even scarier images.
AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
