Posted on 10/24/2016 7:55:30 PM PDT by BenLurkin
They call it the 'Nightmare Machine'.
It's learnt a number of styles , from 'Fright night' to 'Inferno', which the team has applied to a bunch of famous landmarks from around the world....
As well as buildings, the team has been working on making people's faces scarier. That algorithm has been taking a bit more tweaking, and to that end the team wants your help rating whether a selection of faces are scary or not to improve it.
"Creating a visceral emotion such a fear remains one of the cornerstones of human creativity,"
(Excerpt) Read more at techradar.com ...
MIT knows what’s important , D’oh
nice selfies !
It works!
It’s not a bug, it’s a feature!
Cool stuff.
Deep learning is making real progress these days.
Thanks for posting!
That’s scary.
This hard work and deep thinkin’ in AI to achieve? A 10 year old could’ve done it in Photoshop in two minutes.
Looks like the AI was fed a bunch of French Impressionist styles with a touch of Dali and Picasso.
It only takes the computer 20 nanoseconds ...
Oh crap!!!!
Now that scares the beejeepies out of me.
OH, well, that is different. We’re looking at a giant leap for man in silly graphics, then.
In before the Helen Thomas pic.
Hah!
Perhaps we should devise an AI that makes MIT students apply themselves to their proper studies...
What a waste of time. Do they offer degrees in cat videos too? The only thing that makes me feel a little better about this is that all the students there are probably Chinese. So they’ll return home with the skills to make the tiger **** on their menus look a little funnier.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.