Date: Thursday, May 27
Start Time: 1:30 pm
End Time: 2:00 pm
Recent progress in machine learning algorithms has been meteoric. Yet their implementation in real-world embedded applications crawls at a snail’s pace, in large part due to inconsistent and inefficient software architectures. In this session, we will introduce the concept of software containerization, explain how it works, and examine how a containerized deployment methodology at the edge can circumvent barriers that currently hinder the deployment of new and improved ML algorithms. We’ll also explore the trade-offs and limitations of using containerization, and show how we have used containerization to enable new capabilities like mask detection and license plate recognition to be quickly deployed on to existing cameras.
