Blog post

Recap: Edge Impulse at NVIDIA GTC24

Machine Learning
By Edge Impulse Team
Recap: Edge Impulse at NVIDIA GTC24

As the week comes to a close, we're celebrating an incredible experience at NVIDIA's annual GPU Technology Conference, better known as GTC. Always a stellar event, this year really stood out with its size and scale, impressive array of exhibitors, and an absolutely engaged audience of attendees. Not to mention the keynote at the SAP Center that felt like a concert of its own.

Announcements

Edge Impulse hosted a booth at the show, and with it, brought some big announcements. Here's a rundown:

• NVIDIA TAO Toolkit Integration: With Edge Impulse, engineers can now deploy the best-in-class TAO visual AI models to any type of device from any maker, including power-efficient MCUs.

• NVIDIA Omniverse Integration: Augment your datasets with viable synthetic data, and validate your Edge Impulse-generated models with Omniverse digital twin functionality.

• NVIDIA Jetson Orin hardware support: Get high-powered GPU processing for your edge solutions with NVIDIA's Jetson Orin, now natively supported in Edge Impulse.

Overheard:

"TAO object detection on MCUs, that's badass." —NVIDIA engineer at Edge Impulse's GTC booth

Edge Impulse/NVIDIA press coverage

Our NVIDIA integration announcements received a number of articles in various media outlets through the week:

• EETimes: "Edge Impulse Brings Nvidia’s Tao Toolkit To TinyML Hardware" By Sally Ward-Foxton 

Edge Impulse machine learning platform adds support for NVIDIA TAO Toolkit and Omniverse - CNX Software
Edge Impulse machine learning platform for edge devices has released a new suite of tools developed on NVIDIA TAO Toolkit and Omniverse that brings new AI
NVIDIA Is Being Pushed to the Edge
A collaboration between NVIDIA and Edge Impulse is increasing the accuracy of edge ML models deployed on resource-constrained devices.
The 21 Hottest Products At Nvidia GTC 2024
CRN looks at 20 new hardware and software products from Nvidia’s technology partners based on the latest Nvidia GPU and other offerings.
Edge Impulse taps Nvidia Omniverse for edge AI
Edge Impulse has released a new suite of tools developed on Nvidia’s Omniverse and AI platforms to bring the latest AI models to the edge
Edge Impulse brings NVIDIA-powered models to edge MCUs, MPUs, and AI accelerators | Edge Industry Review
This initiative hopes to extend the reach of AI models to a previously untapped category of devices situated at the edge.
Run Nvidia Tao-developed AI vision models on non-Nvidia Arm hardware
Custom vision-based AI software created on Nvidia’s Tao tool set can be run on Arm based Cortex-M, Cortex-A and Ethos-U microcontrollers according to Edge

And more coverage from:

• EE Journal
• SDX Central

Event activities

Any good event exhibitor has various activities going on in their booth and at the show.

• Senior Dev Rel Engineer Jenny Plunkett presented "Swift Path to Edge AI: Revolutionizing Development Through Synthetic Data"

• AI at the Edge book signing: Co-authors Jenny Plunkett and Daniel Situnayake deftly managed a line that extended around the Edge Impulse booth of attendees waiting to get their own signed copy of the O'Reilly book.

• Edge Impulse gave away an NVIDIA Jetson Orin dev kit each day (Winners: Calvin Lam, Cabe Atwell, and Robbie Jerrom)

• Presentation: "Getting AI to the Edge with NVIDIA Jetson Orin, Edge Impulse, and Lumeo" Jenny Plunkett represented Edge Impulse in this Jetson Day presentation with Lumeo's Devarshi Shah.

• Edge Impulse socks: Who'd have thought that one of our most popular social posts from this week would have been an image of NVIDIA CEO/founder Jensen Huang, carrying a pair of our special Edge Impulse-branded socks?

Edge Impulse on LinkedIn: #gtc24 #edgeai #leadership #innovation #ai
When the CEO of NVIDIA stops by your booth and gets his own pair of toasty Edge Impulse socks. Great moment at #gtc24, making strides together in the world of…

• Lots of great conversations: We met so many interesting people this week, and look forward to continuing our discussions with them all.

We thoroughly enjoyed the show, and can't wait to come back next year. Thank you to NVIDIA for having us, and to all those who stopped by to say hello. Contact us anytime to talk about your own edge AI needs.

Comments

Subscribe

Are you interested in bringing machine learning intelligence to your devices? We're happy to help.

Subscribe to our newsletter