AI has become a major driver of edge computing adoption. The edge computing layer was originally only meant to deliver lower compute, storage and processing capabilities to IoT deployments. As well as for  sensitive data that could not be sent to the cloud for analysis and processing is also handled at the edge.

Here’s an overview of the players and the state of the edge computing art.

Three AI accelerators present on the market today are NVIDIA Jetson, Intel Movidius and Myriad Chips, and finally the Google Edge Tensor Processing Units. All three are highly optimized for edge pipeline workflow and will see an increase in usage over the coming years. As AI continues to become a key driver of the edge, the combination of hardware accelerators and software platforms is becoming important to run the models for inferencing. By accelerating AI inferencing, the edge will become an even more valuable tool and change the ML pipeline as we know it.

You can now derive rich insights from your IoT data in Azure Time Series Insights using advanced visualization options.

The team has introduced  several new capabilities into TSI Explorer since we launched last December. These include significant Performance improvements, new Explorations like Scatter Plots & Heatmaps, as well as an enhanced JS SDK and more. Rahul Kayal, PM in the TSI team walks us through the latest additions and enhancements in TSI.

Check this video out to learn more.     

Try Azure Time Series Insights today: https://aka.ms/tsipreview
Check out the JS SDK for TSI in action: https://aka.ms/tsiclientdemos
Try Azure IoT for free today: https://aka.ms/aft-iot

Imagine a Raspberry Pi cluster computing kit for $128. Well, imagine no more. Just think of what AI-infused IoT geeky things that could be built with this.

Raspberry Pi computers have been quite the revolution for makers, encouraging experimentation and creativity thanks to their low cost and compact size. And while the tiny computers are by no means high-end in their processing power, they continue to get faster with each generation. Now, you can gang together […]

The Raspberry Pi 4 Model B is the latest version of the low-cost Raspberry Pi computer platform. In short, it’s a credit-card sized electronic board that can function as a stand-alone computer.

The Raspberry Pi 4 can do a surprising amount. Amateur tech enthusiasts use Pi boards as media centers, file servers, retro games console, routers, and network-level ad-blockers, for starters. However that is just a taste of what’s possible. There are hundreds of projects out there, where people have used the Pi to build tablets, laptops, phones, robots, smart mirrors, to take pictures on the edge of space, to run experiments on the International Space Station — and that’s without mentioning the more wacky creations — teabag dunker anyone?

The Raspberry Pi 4 could not have come at a better time and now is the moment for new developers to start experimenting with the technology. This powerful, yet tiny, computer can be used for a variety of functions, but our focus today will be on using the Pi 4 for image processing in a small package and low power setting.

The computing power of the Raspberry Pi 4 is higher compared to previous generations. This means that it can perform inference fairly quickly. It can be used for various types of applications. These include a rock-paper-scissors detection machine, home surveillance through motion detection, object detection for authorized entry (pet vs. animal) or even to give vision to a robot.

I’ve often referred to edge computing in many posts, but here’s a great article on why it will revolutionize IoT and help it really transform entire industries along with our everyday lives.

The edge is where data gets generated, events occur, things and people interact. The key is putting intelligence there. The Internet of Things (IoT) holds great promise for improving operational efficiencies and vastly reducing costly downtime. But for IoT to realize its potential, computational challenges must be overcome. Even […]