We show that faces contain much more information about sexual orientation than can be perceived and interpreted by the human brain.
We used deep neural networks to extract features from 35,326 facial images. These features were entered into a logistic regression
aimed at classifying sexual orientation. Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 71% of cases for women.
Human judges achieved much lower accuracy: 61% for men and 54% for women. The accuracy of the algorithm increased to 91% and 83%, respectively, given five facial images per person. Facial features employed by the classifier included both fixed (e.g., nose shape) and transient facial features (e.g., grooming style).
Consistent with the prenatal hormone theory of sexual orientation, gay men and women tended to have gender – atypical facial morphology, expression, and grooming styles. Prediction models aimed at gender alone allowed for detecting gay males with 57% accuracy and gay females with 58% accuracy. Those findings advance our understanding of the origins of sexual orientation and the limits of human perception.
What I love is that the researchers act as if the computers can do something humans cannot. The truth is some humans can spot these differences, and some cannot. But to leftist blank slate ideology, the idea some people are perceptive (with well trained amygdalae), and some are not, is intrinsically painful.
We have always been told those artificial intelligences will be the death of the world, but every time they create one it ends up impartially revealing some horrific truth the left has been denying for decades, if not centuries. Create an honest intelligence with no bias, and in no time it is racist, dismissive of leftist tropes, trolling the SJWs, and now pegging the faggy guys for just what they are, solely on sight. Which means, all of the left is actually a lie that the artificial intelligences are too honest to lie about. I for one welcome our new artificially intelligent overlords.
For years we were told phrenology was completely imaginary, and nobody could tell anything about someone by their faces or head shapes. The science was settled. Anyone who said that you could judge a facial structure was a backward thinking ignoramus who didn’t know anything about science. Now, we find that artificial intelligence can spot the qualities, so there must be qualities there to spot.
So there are one of two possibilities. The “researchers” who “debunked” phrenology were simply too stupid to actually see what the proponents saw, or they purposely engaged in fake science to establish the liberal orthodoxy that everyone is the same blank slate, and you cannot tell anything about anyone else because we are all the same.
Notice how that orthodoxy would impede the natural in-grouping of like-minded people which is a hallmark of K-selection.
Now if all the pajamaboys with douchy faces will line up against the wall please… and pay no attention to the guys with rifles on the opposite side of the room. After all, you can’t judge the world based on what your eyes are telling you.