The particular street signs, windows, and balconies on this street mark it as Parisian.
Paris, the city of light, is instantly recognizable—as long as you’re looking at a photo of the Eiffel Tower or the Louvre. But could you recognize the city if the picture lacked a flashy landmark? (Try testing yourself here—just don’t look at the text on signs.)
If you find yourself stumped, know that a new software program has you beat: it can identify a city from a single photo of any old street. Almost any street, the program’s designers found, has little details that give away its city, including distinctive street signs, windows, and balconies.
Chances are, your hard drive is packed with important relics—the first email you sent your spouse, the photographs of your grandma’s 80th birthday, the documents you read for your senior thesis. The data you’ve accrued plays the same role as albums full of pictures, letters, and sentimental objects might have for earlier generations: it constructs a narrative about your progress through life. Or at least it could, if there were a way to have it automatically organized.
This personal data-mining is what what Facebook’s Timeline feature aims to do, but the Timeline is curated manually by the user, includes only files you’ve uploaded to Facebook, and is public, for all your Facebook friends to see (and maybe there are some events in your life you’d like to remember without the whole world peering over your shoulder). So we were interested to read about Lifebrowser, a product being developed in Microsoft Research that automatically arranges your hard drive’s files into a timeline, using machine learning to discern which of them represent landmark events.