ВИФ2 NE : Ветка : первоисточник для владеющих - Стивен Вольфрам пишет такое вот

Про успехи и ошибки ИИ в распознавании картинок (многаненашихбукав, но с картинками) -

http://blog.wolfram.com/2015/05/13/wolfram-language-artificial-intelligence-the-image-identification-project/

Интересные промахи:

http://blog.stephenwolfram.com/data/uploads/2015/05/unexpected-images-tested-with-imageidentify.png

"Почти человеческие ошибки"

http://blog.stephenwolfram.com/data/uploads/2015/05/strange-inputs-to-imageidentify.png

Доставляет картинка Имперского Бронехода в снегу, опознанная как "лыжник".

И объяснения (вкратце - фоновые объекты часто повторяются на несвязанных картинках):

Sometimes we saw things that at first seemed completely crazy. A pig misidentified as a “harness”. A piece of stonework misidentified as a “moped”. But the good news was that we always found a cause—like confusion from the same irrelevant objects repeatedly being in training images for a particular type of object (e.g. “the only time ImageIdentify had ever seen that type of Asian stonework was in pictures that also had mopeds”).

===> dic duc fac <===