Talk / Overview

At Facebook, machine learning provides a wide range of capabilities that drive many aspects of user experience including ranking posts, content understanding, object detection and tracking for augmented and virtual reality, speech and text translations. While machine learning models are currently trained on customized datacenter infrastructure, Facebook is working to bring machine learning inference to the edge. By doing so, user experience is improved via reduced latency and network dependencies. Furthermore, this also enables more applications of deep learning with important features only made available at the edge. This paper takes a data-driven approach to present the opportunities and design challenges faced by Facebook in order to enable machine learning inference locally on smartphones and other edge platforms.

Talk / Speakers

Brandon Reagen

Research Scientist, Facebook

Talk / Slides

Download the slides for this talk.Download ( PDF, 11565.23 MB)

Talk / Highlights


Machine Learning at Facebook: Understanding Inference at the Edge

With Brandon ReagenPublished March 12, 2020

AMLD / Global partners