Facebook Is Creating The World’s Most Detailed Map With The Use Of Artificial Intelligence

By Samir Ghanmi | Feb 24, 2016 05:33 AM EST

TEXT SIZE    

Facebook's intention is to get all users to access online, either by networking or even hi-flying drones. For that to happen, it has to pin point each user's location.

Americans occupy a very detailed mapped out world. If a user types in "Burger King" so to speak into an input online box, Google will deliver different nearby options to choose from precisely based on the longitude and latitude of a user's position.

Facebook's global head of engineering and infrastructure Jay Parikh, and head of Connectivity Lab Yael Maguire, both lead a group of journalists through the proceeding of building the maps.

Yael Maguire says, "Our goal is to figure out how we can develop technologies and understanding how we can connect every person on the planet," where the current best source for mapping of population data can be found in Columbia University, although it needs more detailing because it only provides 1 km resolution. He also states that, "If we want to think about the best technology to connect people especially outside of the cities, this is a very misleading piece of information."

Facebook's Connectivity Lab joined up with artificial intelligence company and data science almost a year ago.

For Facebook's first run gave out imagery from 20 countries that managed to cover 21.6 million square kilometers. Facebook's artificial intelligence team managed to munch up 14.6 billion images in total. The group's technique depended on standard machines, to evidently locate the people's settlements in images. Using Facebook's data centers machinery, it thought to figure out with an algorithm to retrieve contained images evidently showing people's settlement by showcasing large training set and everything is done on its own.

The outcome for this process is to map out intricate parts of people's settlements that's currently being available in different countries.

Maguire said, "This data set is something we are very excited about," and he also says, "We are interested in getting feedback from the global community on how it can be used for connectivity analysis."

pre post  |  next post
More Sections