Flickr is using Deep Learning to auto-tag images

Artificial Intelligence , Big Data , Content & Media , Rudy de Waele

Shortly after unveiling its updates to build bigger and faster neural nets, now Nvidia explains in a blog post how it helped Flickr build its “Magic View” auto-tagging feature that can sort through all of the 11 billion images on its servers.

Of course, the engineers at Nvidia know that there’s nothing “Magic” about Magic view, but to someone who isn’t quite as lavishly familiar with the technology it can certainly appear to be so, especially if you have a somewhat decent understanding of how difficult some computer algorithms are to create. It’s quite easy to ask a human being what brand a certain car is, but programmers will think you’re pulling their leg if you ask them to write a program to do the same task — the software required to do so is all but simple.

Deep Learning solves that problem, but not in a particularly simple way. By feeding the Deep Learning software many images, it can learn the content of these images by recognizing various patterns. It then learns these patterns and can use them to recognize similar things in other images. All of these patterns are stored in the deep neural network (DNN) in the form of vectors.

Read the full article.

Posted by Rudy de Waele aka @mtrends / shift2020.com

Rudy de Waele

Discuss

Cookies & Policy

By using this site you agree to the placement of cookies in accordance with our terms and policy.