Edge AI in a 5G world

Alex Cattle

on 6 February 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

Talk to us today

Interested in running Ubuntu Desktop in your organisation?

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

Ubuntu Core: an independent security analysis

This is a guest blog by Trent R.Hein, Co-CEO of Rule 4. Once in a while an opportunity comes along that brings out our inner geek like no other, which is what...

Edge AI in a 5G world – part 4: How your business can benefit from ‘smart cell towers’

This is part of a blog series on the impact that 5G and GPUs at the edge will have on the roll out of new AI solutions. You can read the other posts here....

Edge AI in a 5G world – part 3: Why ‘smart cell towers’ matter to AI

This is part of a blog series on the impact that 5G and GPUs at the edge will have on the roll out of new AI solutions. You can read the other posts here....