Re:Deep neural networks more accurate than humans at detecti...
by speedplane on Friday September 08, 2017 @06:54AM
(#15199282)
If the test set of images really were 50/50 and the human judges weren't told that, then they were effectively given inaccurate priors, which would obviously reduce their accuracy.
From what I can gather he's basically saying that the "probability of a random face being classified as homosexual" is 0.5. This isn't REALLY true (would have to run the classifier on all possible faces to find this), but that is in fact the "environment" the classifier has been trained within.