Virtual Robots Fooled By Visual Illusions
Roland Piquepaille alerts us to research out of University College London in which virtual robots, trained to "see" as we do, were duped by optical illusions the same way humans are. Here's one of the illusions the software system fell for.
From TFA: "The virtual robots in this study were driven solely by the statistics of their training history and used these statistics as the basis of their correct and subsequent incorrect decisions. Similarly, we believe the human brain generates perceptions of the world in the same way, by encoding the statistical relationships between images and scenes in our past visual experience and uses this as the basis for behaving usefully and consistently towards the sources of visual images." So the robot vision was created as a model of human vision, and it succeeded at doing so. That's sort of interesting, I suppose, but what does it tell us? That we were right about the way human vision works? Seems to me that the point here is really that in some ways, human vision is 'broken' and that maybe it isn't the best apparatus for machines to use. If we want to welcome our robotic overlords, we should be improving on the vision model, not trying to give machines the same flawed framework.
and your eyes do it to. Which is why even sodium vapor lights don't look as yellow as they really are by the human eye. Turn off the white balance on the robots and I bet you they will see them as the same color. Add the average inverse color as a background for each color and your eyes will see them totally different. IE blue behind the orange and orange behind the blue. really stupid test.
OMG Ponies!!! with Glitter!!!! I miss Pink
I think it is important to problem small weaknesses into our robots. You know, just in case.
This is why I turn my auto-white-balance off in my digital camera. If I need to adjust the color, I'll do it later in Photoshop. (Another reason to shoot in RAW mode.) -- Carey
I came here to post the exact same experience. I'm red-green colorblind; they look the same to me.
OT question, since you're also colorblind and I'm curious: does your girlfriend wear makeup? See, mine does.
WHO IS SHE WEARING IT FOR?
Don't put advice in your sig.
The error lies in presupposing that the question is really asking "what would this pixel color be in reality" rather than just "what's this pixel color on this screen". Once you are told that it's an "optical illusion" you can focus merely on the two center squares and determine that they are indeed the same color. Just as a computer program can be trained to ignore the surrounding image. I think it's more of a trick question if anything.
No matter what I'll put my money on a radiometer over the human eye any day of the week.
you don't want to know
-Clio
Karma: Bad (mostly from not giving a fuck)
Blog: http://clintjcl.wordpress.com
The program wasn't designed to detect optical illusions -it was a by-product of the training the system went through. The fact that it was tricked by a similar illusion without being programmed to do so might be taken as suggestive that our learning mechanisms are similar to the ones used by the program. From TFA:
These days, Roland's links go to the original story. Originally, his links went to his blog, as others have described. I don't his current posts. His previous ones, though, were just a bit self-serving.
Program Intellivision!