TechXchange: AI on the Edge

Content, videos, and podcasts address edge AI topics.
Related To: 
June 25, 2026
2 min read
Add Us On Google

In This TechXchange

 

ID_446024224_Andrei_Dodonov_Dreamstime
6a3d93d4d746c2e45d1e2531 Promo Id 446024224 Andrei Dodonov Dreamstime

Looking to run large language models (LLMs) on the edge? Will a convolutional neural network (CNN) help your application identify something? What kind of hardware do I need to run artificial-intelligence/machine-learning (AI/ML) models at the edge? What are spiking neural networks (SNNs)?

These and other questions are addressed by content in this TechXchange. The articles, videos, podcasts, and polls were selected by Electronic Design editors. TechXchanges are also updated as we post new content on topics like this.

Edge AI on Inside Electronics

Edge AI-Related TechXchanges

These TechXchanges cover topics similar, or related, to artificial-intelligence processing at the edge.

271129759 © Ruslan Batiuk - Dreamstime.com
271129759__ruslan_batiuk__dreamstime
Generative artificial intelligence (AI) like chatbots are changing the way many use AI.
AI and machine learning, including tinyML, can run on microcontrollers and small SoCs.
monsitj / iStock via Getty Images
High-Quality Software
High-quality software requires good programmers using the right tools and methodologies.
ID 38307812 © Cammeraydave | Dreamstime.com
id_38307812__cammeraydave__dreamstime
Search for a TechXchange
ID 38307812 © Cammeraydave - Dreamstime.com
promo_id_38307812__cammeraydave__dreamstime
Check out the newest TechXchanges on Electronic Design
Check out all our topic-focused TechXchange content collections.

Edge AI Foundations and Strategy

These articles examine the evolution of edge AI and why intelligence is moving from the cloud to endpoint devices. They explore the opportunities and challenges developers face when deploying AI at the edge.

DigiKey; Getty Images/gremlin
promo_web
As demand for real-time intelligence grows, edge AI is well-positioned to continue its substantial impact in many industries.
91432351 © Kittipong Jirasukhanont | Dreamstime.com
Ai Dreamstime L 91432351
Artificial intelligence belongs on the edge, where it can do things that are beyond the scope of people.
ID 126723440 © Sompong Sriphet | Dreamstime.com
smartfactory_dreamstime_l_126723440
Some answers to key edge AI implementation questions, from modeling to hardware selection.
170145228 © Denis Kobzev | Dreamstime.com
aicomputing_dreamstime_l_170145228
Intelligence and the edge—what could possibly go wrong? Plenty, it turns out, whether it’s power limitations or security concerns, among other issues.
142816613 © kkssr | Dreamstime.com
Ai Dreamstime L 142816613
Artificial intelligence is furthering its way into everyday lives, but the focus has predominantly been on the “big machines,” such as self-driving cars. Perhaps it’s now time...
DFI and 12939076 © Marianne Campolongo | Dreamstime.com
Board Dreamstime L 12939076
Highlights of DFI's exhibition include high-performance industrial motherboards featuring AMD's 1.8-in. Ryzen, Intel's newest Raptor Lake-S and Alder Lake series processors, and...
Some results of our recent machine-learning survey were expected, but others raised eyebrows.
321753871 © warunporn thangthongtip | Dreamstime.com
ai_dreamstime_l_321753871
Although artificial intelligence is a significant technology advance, it also serves as a reminder of how technology disruption has impacted society in the past.

Go to Table of Contents

AI Hardware at the Edge

AI applications can run on the edge using conventional processing hardware, but AI acceleration can significantly reduce power consumption and provide much more performance. It also reduces latency and communication overhead required by cloud-based solutions. These articles look at the computation side of edge AI solutions.

Arm’s Cortex-A320/Ethos-U85 NPU platform delivers low-power, high-performance AI.
Infineon Technologies
Promo
Infineon’s PSoC Edge adds machine-learning support to its configurable microcontroller.
iStockphoto
Siemens Eda Promo
Code reduction and simple verification are just two of the benefits that high-level synthesis brings to AI acceleration.
Particle
promo_web
Particle’s new 5G-capable Tachyon single-board computer brings AI acceleration to spark innovation and drive embedded and AIoT applications.
Elma Electronic and Dreamstime_Prostockstudio_197381140
Brain Dreamstime Prostockstudio 197381140 Promo
Elma’s JetSys-5330 is built around NVIDIA’s Jetson AGX Orin.
The Raspberry Pi AI Kit comes with an M.2 HAT+ and Hailo AI acceleration module capable of pushing 13 TOPS.
96442672 | Abstract © Bluebay2014 | Dreamstime.com
cloudcomputing_dreamstime_l_96442672
Artificial-intelligence algorithms, particularly artificial neural networks and their hardware, are critical in addressing edge AI applications.
Dreamstime_Rawgrouppro_24503927
dreamstime_rawgrouppro_24503927
This FAQ introduces and explains the new eUSB2 and eUSB2V2 standards, targeted at inside-the-box connections within AI PCs and other edge AI applications.
Microchip’s latest power module targeting AI systems includes integrated I2C and PMBus interfaces for flexible configuration and monitoring.
Dreamstime_prostockstudio_154528336
dreamstime_prostockstudio_154528336
Right-sizing hardware to balance performance, power consumption, and cost enables machine learning to run on resource-constrained platforms.
Very few areas of industry will escape the influence of artificial intelligence, with many applications involving security and safety measures.

Go to Table of Contents

Generative AI on the Edge and More

Running sophisticated AI models on resource-constrained devices requires advances in model architecture, software optimization, semiconductor technology, and design automation. These articles explore edge AI topics including generative AI, explainable AI, and AI-enhanced engineering tools.

The increasing demands for generative AI at the edge call for new solutions that can achieve high performance within the low-power requirements for edge apps.
ID 319400129 © Dmytro Lopatin | Dreamstime.com
ai_dreamstime_l_319400129
AI infusion amplifies engineer’s abilities and the systems capabilities as well as shortens the development time. Faster results, easier design, and flawless code is possible....
Embedded-systems designers are on a mission to squeeze powerful AI algorithms into resource-constrained gadgets, relying on cutting-edge custom hardware accelerators and high-...
95793105 © Vchalup | Dreamstime.com
Ceva Dreamstime M 95793105
Explainable AI (XAI) can improve safety, security, and the overall user experience in IoT applications.
Artificial intelligence and more specifically, machine learning, with human augmentation requires a thorough strategy to achieve a breakthrough.
Dreamstime_asliyuce_2829564261
dreamstime_asliyuce_2829564261
AI is transforming semiconductor design by automating tedious tasks, enhancing creativity, and enabling innovative chip architectures, all while addressing the growing workforce...
Ekkasit919_978459716 |iStock / Getty Images Plus
Ekkasit919_978459716 |iStock / Getty Images Plus
Analog designs are challenging, but artificial-intelligence optimizations are improving and speeding up the design process.

Go to Table of Contents

Industrial Automation, Robotics, and Vision in Real-World Applications

Edge AI is increasingly deployed where real-time decision-making is critical — from factory floors and inspection systems to robotics, smart cameras, energy infrastructure, and video analytics. These articles demonstrate how AI is solving practical operational challenges while improving safety, efficiency, and autonomy.

The new processor family from Texas Instruments can handle vision and AI processing for up to 12 cameras.
The convergence of high-powered edge AI and smarter video cameras revolutionizes vision systems in their delivery of real-time awareness and responses.
225981180 © Media Whalestock | Dreamstime.com
Edge Computing Promo
Edge AI tools continue to improve and become more powerful, leading the way to a new era of intelligent video analytics with rapidly expanding capabilities and possible uses.
Dreamstime_Yuri-Hoyda_166510122
Robot Arm Dreamstime Yuri Hoyda 166510122
Embedded smart-camera platforms with easy-to-use edge learning provide a unique solution for apps that are too difficult for conventional rule-based machine vision but don’t justify...
ID 321417390 | Ai © Stuardesa77 | Dreamstime.com
robotics_dreamstime_l_321417390
AI integration within robots changes everything about workflows, but it requires workforce retraining to mitigate job replacements.
Dreamstime_irinafoto_333279662
assembly_dreamstime_irinafoto_333279662
AI is moving to the edge, and that’s a good thing. But designers must prepare for voracious power demands and be ready with the right hardware and the right strategies to optimize...
ID 436948156 | Ai © Olga Demina | Dreamstime.com
arc_dreamstime_436948156
DC arc fault detection is undergoing a transformation thanks to edge AI, helping power systems spot dangerous faults faster, locally, and before they cause costly failures.
Transforming "smart" devices into "intelligent" components via AI requires more than computational power. It will be enabled by other technologies, most of which rely on new materials...
NVIDIA
promo
The digital-twin platform, Earth-2, uses AI and machine-learning models for improved weather predictions with enhanced visualizations.

Go to Table of Contents

Electronic Design Videos About Edge AI Topics

For those who like to watch videos, we’ve collected some of our videos covering edge AI topics.

The machine-learning support from Synaptics' Katana SoC can visually detect actions like falling.
Femtosense
Trailer
Femtosense's SPU-001 coprocessor delivers low-power AI audio processing.
A novel edge AI video analytics platform built by Elma Electronic, Hailo, and Isarsoft challenges how business intelligence is addressed in the transportation industry.
PSOC Edge opens the door to a new generation of responsive machine-learning-based, user-centric edge devices.
Dr. Sailesh Chittipeddi, Executive VP & General Manager for IoT & Infrastructure at Renesas, talks about artificial intelligence in edge-computing nodes.
This application example uses the B-U585I-IOT02A Discovery Kit, STM32Cube.AI Developer Cloud, and AWS’ solutions to run an audio classification model on an STM32U5 MCU.
The Cadence Tensilica AI Platform delivers scalable and energy-efficient on-device to edge AI processing.
Offering protection against high voltage and noise interference, Analog Devices' iCoupler isolation technology can create edge AI systems for harsh and high-voltage environments...

Listen to Inside Electronic Podcasts about Edge AI Topics

And for those who like to listen to podcasts, we’ve collected some of our Inside Electronics episodes covering edge AI topics.

Dreamstime_Busakorn-Pongparnit_93315266
dreamstime_busakornpongparnit_93315266_promo
Inside Electronics
Just as we migrated from basement mainframes to desktop computers, our modern infrastructure is migrating from the server to the edge.
Inside Electronics
Synaptics’ Vikram Gupta talks about artificial intelligence and the Astra SR100 Series.
Dreamstime_Ekkasit919_125698314
dreamstime__ekkasit919_125698314
Inside Electronics
Artificial intelligence is a logical progression in edge computing and automated testing. However, it’s important to understand how best to deploy AI in a system.
Dreamstime_Ahmadrizal7373_336311969
dreamstime_ahmadrizal7373_336311969_promo
Inside Electronics
Advanced systems, technologies, and solutions migrating into the cloud and edge computing is creating both opportunities and challenges for those creating the future infrastructure...
Dreamstime_Rolffimages_15597877
dreamstime_rolffimages_15597877_promo
Inside Electronics
Find out how to do AI processing of multiple video streams locally.
Inside Electronics
Femtosense CEO Sam Fok talks about AI/ML on the edge and the company’s dual-sparsity processing unit.
ID 322680569 © Alexandersikov | Dreamstime.com
dreamstime_alexandersikov_322680569
Inside Electronics
Femtosense CEO Sam Fok weighs in on the challenges and benefits of implementing sparse AI for real-time edge applications.

Go to Table of Contents

Find Out What Readers Think About Edge AI

Below are some of our quick polls that address edge AI. Take one to see what other engineers and programmers think about the technology.

Do you use large language models in generative AI, and if so, what is their main function?
Take a quick poll and see what other programmers are up to.
As Mad Magazine's Alfred E. Neuman said, "What, Me Worry?"
Chatbots and AI/ML software is flooding not only the general markets, but software-development arenas as well.

Go to Table of Contents

About the Author

William G. Wong
Email

William G. Wong

Senior Content Director - Electronic Design and Microwaves & RF

I am Editor of Electronic Design focusing on embedded, software, and systems. As Senior Content Director, I also manage Microwaves & RF and I work with a great team of editors to provide engineers, programmers, developers and technical managers with interesting and useful articles and videos on a regular basis. Check out our free newsletters to see the latest content.

You can send press releases for new products for possible coverage on the website. I am also interested in receiving contributed articles for publishing on our website. Use our template and send to me along with a signed release form. 

Check out my blog, AltEmbedded on Electronic Design, as well as his latest articles on this site that are listed below. 

You can visit my social media via these links:

I earned a Bachelor of Electrical Engineering at the Georgia Institute of Technology and a Masters in Computer Science from Rutgers University. I still do a bit of programming using everything from C and C++ to Rust and Ada/SPARK. I do a bit of PHP programming for Drupal websites. I have posted a few Drupal modules.  

I still get a hand on software and electronic hardware. Some of this can be found on our Kit Close-Up video series. You can also see me on many of our TechXchange Talk videos. I am interested in a range of projects from robotics to artificial intelligence. 

Sign up for our eNewsletters
Get the latest news and updates

Related

Comment About the Article

To join the conversation, and become an exclusive member of Electronic Design, create an account today!