09-24-2015, 04:01 PM
Google's image recognition system is now at least as good as that of the average human.
http://magazine.utoronto.ca/feature/gett...-machines/
"The practical uses for sophisticated image recognition seem almost endless, but one of Hinton’s projects is deceptively simple: getting a machine to read handwritten numbers. With great effort, he and his colleagues at Google have pulled it off. The software they’ve developed lets Google read the street addresses on people’s homes (vital for connecting the data from its 'map' function to its 'street view' function). 'The techniques we developed for that are now the best way of reading numbers in the wild,' Hinton says. 'And the neural nets are now just slightly better than people at reading those numbers.'"
http://magazine.utoronto.ca/feature/gett...-machines/
"The practical uses for sophisticated image recognition seem almost endless, but one of Hinton’s projects is deceptively simple: getting a machine to read handwritten numbers. With great effort, he and his colleagues at Google have pulled it off. The software they’ve developed lets Google read the street addresses on people’s homes (vital for connecting the data from its 'map' function to its 'street view' function). 'The techniques we developed for that are now the best way of reading numbers in the wild,' Hinton says. 'And the neural nets are now just slightly better than people at reading those numbers.'"