0

February 8, 2017 AT 10:00 am

Can an MIT Computer Learn to Scare You? #ArtificialIntelligence

Louvre

Via NPR

A bloody Taj Mahal. A haunted Colosseum. A toxic Capitol Hill.

Welcome to the “Nightmare Machine,” a horror-imagery project created by three researchers at the Massachusetts Institute of Technology. Pinar Yanardag, Manuel Cebrian and Iyad Rahwan used artificial intelligence algorithms “to learn how haunted houses, or toxic cities look. … Then, we apply the learnt style to famous landmarks and present [to] you: AI-powered horror all over the world!”

The project website is up just in time for Halloween but the method is not new — the algorithm they use is a so-called “deep learning” system published last year by computer scientists, which is capable of creating “artistic images of high perceptual quality” based on examples of images created by humans.

“High perceptual quality” basically means the images look good to people who see them.

The researchers taught the algorithm at least eight horror styles for haunted places: haunted house, fright night, slaughterhouse, toxic city, ghost town, inferno, tentacle monster and alien invasion.

They applied the algorithm’s understanding of the qualities of each style to images of famous landmarks to create creepy computer-generated images of, for example, the Golden Gate Bridge being attacked by a tentacle monster.

See more!


Check out all the Circuit Playground Episodes! Our new kid’s show and subscribe!

Have an amazing project to share? Join the SHOW-AND-TELL every Wednesday night at 7:30pm ET on Google+ Hangouts.

Join us every Wednesday night at 8pm ET for Ask an Engineer!

Learn resistor values with Mho’s Resistance or get the best electronics calculator for engineers “Circuit Playground”Adafruit’s Apps!


Maker Business — Transforming Today’s Bad Jobs into Tomorrow’s Good Jobs

Wearables — Not a loophole

Electronics — Rule of thumb: 10mils per amp.

Biohacking — Soft Artificial Human Heart #3DThursday #3DPrinting

Get the only spam-free daily newsletter about wearables, running a "maker business", electronic tips and more! Subscribe at AdafruitDaily.com !



1 Comment

  1. Really the way to do this is to put people on something like a polygraph and let the neural net train directly from their physiological responses when they see these images. That might sound silly, but it could easily lead to new insights into PTSD and anxiety disorders and perhaps directly to effective new treatments. If you’re working with this thing for hours and its neural nets are doing their best to scare you, over time you might start getting bored with the whole exercise, and if so, it would be interesting to see if this had an impact on fearful responses to real-world stimuli.

Sorry, the comment form is closed at this time.