Anatoly Levenchuk (ailev) wrote,
Anatoly Levenchuk

Запомним март 2015г.: компьютеры стали лучше людей в распознавании изображений

Я писал в сентябре 2014 про "почти паритет" между человеком и компьютером в распознавании изображений --

С тех пор произошло много чего интересного ( "In the annual ImageNet competition, the best neural net was able to correctly classify images with a 25.7 percent error rate in 2011. That went to 16.4 percent in 2012, 11.7 percent in 2013, and 6.7 percent in 2014. Baidu showed a paper with a 6.0 percent error rate in January, Microsoft published a 4.9 percent error rate in February, and Google itself published a paper with a 4.8 percent error rate on March 2".

Вот ImageNet --

Вот работа Гугля: Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters --
  • Post a new comment


    Anonymous comments are disabled in this journal

    default userpic

    Your reply will be screened