Nightmare Machine by MIT Media Lab
- Help our algorithm learn scariness by voting our faces !
- We used state-of-the-art deep learning algorithms to generate new faces.
- Horror imagery generated by artificial intelligence.
- We use state-of-the-art deep learning algorithms to learn how haunted houses, or toxic cities look like.
- We apply the learnt style to famous landmarks and present you: AI-powered horror all over the world!
Nightmare Machine: AI-powered Horror
@neuroconscience: Just in time for Halloween MIT introduces their deep-learning based ‘nightmare machine’
We use state-of-the-art deep learning algorithms to learn how haunted houses, or toxic cities look like. Then, we apply the learnt style to famous landmarks and present you: AI-powered horror all over the world!
The mysterious origin of Halloween traditions can be traced back to the ancient pagans festivals celebrated by Celts. The Celtic people marked the day as the end of the harvest season and the beginning of the winter. They believed the transition between the seasons is opening a gate to the world of the dead.
Eastern and Western Civilizations have scripted legends where human-made created entities, artificial beings capable of thinking, feeling, helping or harming others. These creatures would, in many stories, escape the controls of their creators, and gained knowledge and abilities beyond what anyone would have thought.
The spring of 1816 experienced one of the strangest meteorological phenomena ever recorded: a never-ending winter. This resulted three great writers to lock themselves at a mansion at Lake Geneva. Mary Shelley, John William Polidori, Lord Byron had a competition to see who would produce the scariest story ever written. And they all won. Shelley created Frankenstein; Polidory planted the seed of Vampirism; and Byron, in his poem Darkness, narrated by the last man on earth produced the first item of the apocalyptic horror genre.
AI and Horror cross paths: Anne Isabella Milbanke, wife of Lord Byron (the founding father of modern Vampire literature) gives birth to Ada Lovelace, a pioneer in the history of computation. Ada would go on to write the world’s first machine algorithm for an early computing machine that existed only on paper.
1930s movie screens exploit like no other medium before the emotional ride of getting scared in a dark room with strangers. Many movie hits, from Frankenstein, to Dracula, to The Mummy, to The Invisible Man, culminating in Werewolf in London put horror front and center of how the society decides to have a really good time… spawning a creative and lucrative horror-making industry.
1956’s summer, this time a hot one, brings Marvin Minsky and other brilliant minds together at Darthmouth College. In a explosion of creativity, they plant the seeds of what Artificial Intelligence would become: developing programs able to beat humans at checkers, to do complex math… some of these machines were even able to formulate English sentences. Rumours said that the first sentences typed by a computer were… TRICK OR TREAT?
Since centuries, across geographies, religions, and cultures people try to innovate ways of scaring each other. Creating a visceral emotion such a fear remains one of the cornerstones of human creativity. This challenge is especially important in a time where we wonder what the limits of Artificial Intelligence are: Can machines learn to scare us? Towards this goal, we present you Haunted Faces and Haunted Places: computer generated scary imagery powered by deep learning algorithms and evil spirits!