[New post] Google created a neural network that can accurately guess where a photo was taken

Unknown

Thursday, February 25, 2016

Abner Li posted: " Google has trained a neural network, named PlaNet, to figure out where an image was taken down to the city and even exact street level. The machine only needs to analyze a photo's pixels in order to accomplish the task. Specifically, PlaNet is " Respond to this post by replying above this line New post on 9to5Google Google created a neural network that can accurately guess where a photo was taken by Abner Li Google has trained a neural network, named PlaNet, to figure out where an image was taken down to the city and even exact street level. The machine only needs to analyze a photo's pixels in order to accomplish the task. Read more of this post Abner Li | February 25, 2016 at 9:40 am | Tags: Geolocation, Machine learning, Neural networks, photos, PlaNet | Categories: Tech Industry | URL: http://wp.me/p1w6tN-yJj Comment    See all comments Unsubscribe to no longer receive posts from 9to5Google. Change your email settings at Manage Subscriptions. Trouble clicking? Copy and paste this URL into your browser: http://9to5google.com/2016/02/25/planet-neural-network-photos/ Thanks for flying with WordPress.com