HA! https://www.google.de/search?q=mirror&tbm=isch&gws_rd=cr&ei=0xvBVpvIEcGdPoryq4AO … This seems to confirm a (only barely informed) theory of mine: neural networks are helpless with mirrors.
-
-
This Tweet is unavailable.
-
@rehwanne That actually perfectly illustrates the problem! See how it takes contextual knowledge or a frame to see the mirror? - 2 more replies
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.