Facebook's Andrew Tulloch says deep learning has enabled the company's news-feed ranking algorithm to capture more nuance in posts, with textual content interpreted by neural network-based natural-language processing programs. Facebook is heavily leveraging deep-learning models to further its user engagement efforts, with the company's Andrew Tulloch noting predictive analytics has become less relevant as more Facebook posts embed video and images, and the volumes of data analyzed grow exponentially. Tulloch says deep learning also has enabled Facebook's news-feed ranking algorithm to capture more nuance in posts, with textual content interpreted by neural network-based natural-language processing programs. He also notes deep-learning models are being applied to product development by enabling large-scale comprehension of content. For example, Tulloch cites the use of computer-vision, neural-network, deep-learning models to interpret the content of photos posted by users and select those to surface in the "on this day" feature, without spotlighting potentially negative memories.

Facebook achieved web dominance by riding a business model of understanding users and feeding them tailored content 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.

It controls what news we read, whose updates we get and what events we learn about. Its scope, power and influence extend beyond what we could imagine. So who -- or what -- decides what we see? It's literally impossible to sort the News Feed without superhuman brain power -- a problem that only AI can likely solve. At the ReWork summit in Boston on May 25, Facebook research engineer Andrew Tulloch explained how the social network is using emerging technology to prioritize what you see and better serve your needs. Facebook has been known to tweak how its system processes and ranks content in the News Feed, but it recently turned to "deep learning" -- an advanced form of artificial intelligence -- to help sift through information.

At the 2016 Deep Learning Summit in Boston, Andrew Tulloch, Research Engineer at Facebook, talked about some of the tools and tricks Facebook use for scaling both the training and deployment of some of their deep learning models at Facebook. He also covered some useful libraries that they'd open-sourced for production-oriented deep learning applications. Tulloch's session can be watched in full below.

Serving more than a billion people a day, Facebook has its work cut out for it when providing customized news feeds. That is where the social network giant takes advantage of deep learning to serve up the most relevant news to its vast user base. Facebook is challenged with finding the best personalized content, Andrew Tulloch, Facebook software engineer, said at the company's recent @scale conference in Silicon Valley. "Over the past year, more and more, we've been applying deep learning techniques to a bunch of these underlying machine learning models that power what stories you see." Applying such concepts as neural networks, deep learning is used in production in event prediction, machine translation models, natural language understanding, and computer vision services. Event prediction, in particular, is one of the largest machine learning problems at Facebook, which must serve the top couple of stories out of thousands of possibilities for users, all in a few hundred milliseconds. "Predicting relevance in and of itself is a very challenging problem in general and relies on understanding multiple content modalities like text, pixels from images and video, and the social context," Tulloch said.

Deep learning appeared after a long gestation, or all of a sudden. You can take your pick, depending on where you were when mainstream media discovered a collection of statistical and artificial intelligence techniques that seemed to promise a new era of automated predictive analytics. The vote here is for a long gestation, although it's fair to say there is some suddenness about the way deep learning software is pushing a new class of analytics in which applications repeatedly churn through large sets of data, learning to predict likely outcomes as they go. A lengthy birthing process seems in play because, really, deep learning is an updated take on the machine learning process, which in turn was a new take on neural networks, an early form of artificial intelligence in which simulations mimic the human brain's neuron activity by weighting outputs and building connected sets of meaning. What marks deep learning software is use of multiple processing layers.