Facebook achieved web dominance by riding a business model of understanding users and feeding them tailored content...
By submitting your personal information, you agree that TechTarget and its partners may contact you regarding relevant content, products and special offers.
and advertising. And as the social networking company further builds on its strong position, it leans heavily on deep learning models.
"These kinds of deep learning techniques have been really important over the last couple years," said Andrew Tulloch, an artificial intelligence researcher at Facebook.
In a presentation at the Deep Learning Summit in Boston, Tulloch said traditional predictive analytics techniques like logistic regressions used to be the state of the art at Menlo Park, Calif.-based Facebook. In particular, this sort of analytics powered the ranked news feed, in which users are shown posts they're likely to find interesting, as determined by an algorithm.
But Tulloch said that as more posts started incorporating video and images a few years ago, it became harder to classify them using simpler forms of analytics. Additionally, the scale of the data being analyzed started exploding. This made it a good use case for deep learning.
"The scale of this is where it becomes incredibly challenging, but these types of [deep learning] systems have been really impactful in improving rankings," Tulloch said.
In addition to tackling the problem of scale, Tulloch said deep learning allowed Facebook's news-feed ranking algorithm to capture greater subtlety in users' posts.
Understanding text with deep learning
It's not all about images and videos, though. Facebook also uses natural language processing algorithms to interpret textual content and improve the quality of posts shown to users.
Tulloch said Facebook uses an NLP system built around neural networks to identify posts that are excessively promotional, spam or clickbait. The deep learning model filters these types of posts out and keeps them from showing in users' news feeds.
"There's a huge amount of textual content that's being uploaded on Facebook every day, and understanding that is important to improving customer experience," Tulloch said.
Outside of the news feed, deep learning models are helping Facebook develop products by enabling developers to understand content at a large scale.
Deep learning for computer vision
For example, computer vision neural network deep learning models are used to interpret the content of photos users have posted and decide which to surface in the "on this day" feature. This Facebook feature shows users' posts that they made on the same day in past years, but Tulloch said it's important that it not resurface potentially negative memories.
So the models underlying the feature have to interpret images and develop a semantic understanding of what's happening to ensure it's something people would want to be reminded of. It does this in part by identifying people and objects in images and interpreting the context around them.
The models were trained on more than a billion photos that have been uploaded to Facebook over the years, and they have to score in real time millions of new images uploaded each day. Tulloch said this is a huge technical challenge, but one for which the convolutional neural networks his team uses are well-suited.
"The scale of this problem is massive," he said. "But these kinds of computer vision systems are really powerful in understanding what's going on."
It all comes back to keeping users engaged on the social network. Tulloch said deep learning has played an important role in Facebook's ability to do so, filling a crucial need in the company's business model. "A lot of the challenge comes from surfacing the right content at the right time," he said.
Deep learning models look to break out of the black box
What's the difference between deep learning and machine learning?
Deep learning can present distinct problems for the business
Discover deft prepocessing marks deep learning techniques for data preparation