Edge AI in a 5G world

Alex Cattle

on February 6, 2020

Edge AI in a 5G world

Deploying AI/ML solutions in latency-sensitive use cases requires a new solution architecture approach for many businesses.

Fast computational units (i.e. GPUs) and low-latency connections (i.e. 5G) allow for AI/ML models to be executed outside the sensors/actuators (e.g. cameras & robotic arms). This reduces costs through lower hardware complexity as well as compute resource sharing amongst the IoT fleet.

Strict AI responsiveness requirements that before required IoT AI model embedding can now be met with co-located GPUs (e.g. on the same factory building) as the sensors and actuators. An example of this is the robot ‘dummification’ trend that is currently being observed for factory robotics with a view to reducing robot unit costs and fleet management.

In this webinar we will explore some real-life scenarios in which GPUs and low-latency connectivity can unlock previously prohibitively expensive solutions now available for businesses to put in place and lead the 4th industrial revolution.

Watch the webinar

Newsletter signup

Select topics you’re
interested in

In submitting this form, I confirm that I have read and agree to Canonical’s Privacy Notice and Privacy Policy.

Related posts

We are changing the way you build snaps from GitHub repos

On the 11th March 2020 we introduced a new process for building a snap using GitHub repos to snapcraft.io. Here is all you need to know about this update....

GNOME 3.34 snapcraft extension

We constantly strive to empower developers. Part of that aim extends to making development easier, for example improving build tools and documentation. As an...

An adventure through the Snap Store

An application store with a large number of entries is a double-edged sword. It’s often a good sign of a vibrant, thriving community of software creators,...