Edge Devices and LLMs: What's Ahead for AI

James Sweetlove

| Created: June 12, 2024 | Updated: July 1, 2024

Edge Devices and LLMs: What's Ahead for AI

In this episode of the Altium OnTrack podcast, host Tech Consultant Zach Peterson explores the fascinating world of Edge AI and how Large Language Models (LLMs) fit into the picture with Jan Jongboom, co-founder of Edge Impulse. The two discuss the evolution from GPT-2 to GPT-4, the importance of edge computing, and the hardware requirements for running AI on edge devices. Discover how reducing the size of LLMs enables efficient deployment on edge devices, gain insights into the practical applications of AI in various industries, and learn about EDGE IMPULSE.

Listen to the Episode

Watch the Episode

More resources:

Getting started w/ Edge Impulse on Renesas platforms
Connect with Jan on LinkedIn
Learn more about Edge Impulse
Check out a recent video from Edge Impulse: Using GPT-4o to train a 2,000,000x smaller model (that runs directly on device)
Exclusive 15 Days Free Altium Designer Access

About Author

About Author

James Sweetlove is the Social Media Manager for Altium where he manages all social accounts and paid social advertising for Altium, as well as the Octopart and Nexar brands, as well as hosting the CTRL+Listen Podcast series. James comes from a background in government having worked as a commercial and legislative analyst in Australia before moving to the US and shifting into the digital marketing sector in 2020. He holds a bachelor’s degree in Anthropology and History from USQ (Australia) and a post-graduate degree in political science from the University of Otago (New Zealand). Outside of Altium James manages a successful website, podcast and non-profit record label and lives in San Diego California.

More content by James Sweetlove

Related Resources

Can You Use ChatGPT for PCB Design?

Can You Use ChatGPT for PCB Design? ChatGPT is turning everything upside-down, including engineering. Can LLMs be used for PCB design? We’ll take a look at some tasks that can be automated with ChatGPT. Read Article

Using ChatGPT to Analyze Your Test Data

How to Use ChatGPT to Analyze Power Test Data In this article, Ari Mahpour talks about how to best utilize ChatGPT to analyze your battery or power test data. Read Article

How to Build a Custom GPT Action to Talk to Your Hardware

How to Build a Custom GPT Action to Talk to Your Hardware In this article Ari Mahpour shows you how to create custom GPT Actions that will connect with your hardware at home or in the lab Read Article

Retrofitting Lab Instruments with IoT Capabilities Using Generative AI

Retrofitting Lab Instruments with IoT Capabilities Using Generative AI In this article Ari Mahpour shows you how to leverage Generative AI to create a full web service that controls your lab instruments Read Article

Using ChatGPT for Automated Testing

Using ChatGPT for Automated Testing Learn how to utilize ChatGPT for automated testing effectively. Read Article

Embedded AI

The Path Forward for Embedded AI In April 2021, I published an article in Printed Circuit Design & Fab, where I proclaimed the future of AI is embedded. In short, my view is that embedded systems will leverage greater usage of AI on the end device, meaning they will rely less on cloud platforms or data centers for inference. Without a doubt, I believe the future of AI is still embedded, but not with the chipset or system architecture I would have thought. At the time of writing Read Article

The Current State of AI in PCB Design in 2023

The Current State of AI in PCB Design in 2023 Your favorite machine learning, optimization, and generative AI algorithms may soon be used in your favorite PCB design program. Now that ChatGPT has become a household name and competitor companies are developing their own GPT equivalents (Claude, LLaMa, etc.), EDA startups are looking at how to leverage these tools to help PCB designers and engineers be more productive. With so many industries touched by automation and AI, it was only a matter Read Article

Gemini vs. ChatGPT

Gemini vs. ChatGPT: Who Writes Better Code? In this article Ari Mahpour performs a one-to-one coding comparison between ChatGPT’s GPT4 model against Gemini Advanced, Google’s most capable model. Read Article

Yocto vs ubuntu for embedded systems

Yocto vs. Ubuntu: Which OS is Best For Embedded AI? If you’re a programmer, then you know about Ubuntu. It’s one of the standard Linux distros for server environments, and it’s been used in a number of embedded applications. However, there are other, better choices to use for an OS for your next embedded system. Yocto has a steep learning curve, but it may be the best choice for your next embedded application. Read Article

Building an AI Lab Assistant

Building an AI Lab Assistant In this article Ari Mahpour shows you how to put together an AI lab assistant leveraging GPT Actions with ChatGPT Read Article

Related Technical Documentation

Back to Home

Take advantage of the world's
most trusted PCB design system.

One interface. One data
model. Endless possibilities.

Effortlessly collaborate with
mechanical designers.

The world's most trusted
PCB design platform

Best in class interactive
routing

View License Options