While computers have been programmed to detect basic facial characteristics, for example whether a given face is male or female, Kagian’s program is also asked to make a judgment call on aesthetics. While hard-wired to look specifically for face symmetry, skin smoothness, and hair color, Kagian’s computer program also received the results of a survey from a group of people who were asked to rate the attractiveness of a list of faces which the program uses to analyze and learn what people generally consider to be “attractive.”

Says Kagian, “The computer produced impressive results – its rankings were very similar to the rankings people gave.” This is considered a remarkable achievement, believes Kagian, because it’s as though the computer “learned” implicitly how to interpret beauty through processing previous data it had received.

Kagian’s breakthrough highlights another breakthrough for artificial intelligence. We’ve seen how difficult it is for computers to interpret data, whether it’s categorizing different items or answering questions in Jeopardy. However, Kagian’s program shows how computers can even learn human habits and pinpoint the salient features humans look for when they view an object for the first time. While humans are pushing the boundary of what computers are capable of, we, too, are discovering more about ourselves.