Communications of the ACM
How Facebook ses Deep Learning Models to Engage sers
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.
Credit: searchEnterpriseLinux
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. The models were trained on more than 1 billion photos and programmed to score millions of new images uploaded daily, and Tulloch says the convolutional neural networks work well in meeting this challenge.
From SearchBusinessAnalytics
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found