Tiny Machine Learning (TinyML) is the latest embedded software technology that moves hardware into that almost magical realm, where machines can automatically learn and grow through use, like a primitive human brain.

Until now building machine learning (ML) algorithms for hardware meant complex mathematical modes based on sample data, known as “training data,” in order to make predictions or decisions without being explicitly programmed to do so. And if this sounds complex and expensive to build, it is. On top of that, traditionally ML-related tasks were translated to the cloud, creating latency, consuming scarce power and putting machines at the mercy of connection speeds. Combined, these constraints made computing at the edge slower, more expensive and less predictable.

Speaking of NVIDIA, Microsoft Developer takes a look at the latest device in the NVIDIA Jetson line of GPU-accelerated IoT devices, the Jetson Xavier NX.

A device which brings supercomputer-class performance to Edge applications in an ultra-compact form-factor.

To demonstrate this, we configure the device with Azure IoT Edge and deploy the NVIDIA DeepStream SDK Module from the Azure Marketplace to produce object detection telemetry with Azure Stream Analytics then push those results into Time Series Insights and Power BI.

Come see how the pairing of NVIDIA devices and Azure IoT Services make for a first-class solution of AI at the Edge!

Learn more about NVIDIA DeepStream on IoT Edge: https://aka.ms/iotshow/NVIDIADeepStream

Are you a developer implementing, coding or maintaining cloud or edge components of IoT solutions?

Is part of your job to manage devices life cycle – set up, configuration, and maintenance – using cloud services?

Do you design IoT solutions including device topology, connectivity, debugging, and security?

Do you implement solutions to manage, monitor, and transform data related to IoT?

If these job responsibilities sound familiar, I have a great opportunity for you to showcase your skills and be recognized for them: Take AZ-220 exam: Microsoft Azure IoT Developer.

Hear more about the new Microsoft Certified: Azure IoT Developer Specialty and resources to learn how to build IoT solutions with Azure IoT. Visit http://aka.ms/azureiotdeveloper to learn more about the Azure IoT Developer Specialty.

Resources

The combination of 5G and edge computing promises to fast-track the use of artificial intelligence (AI) in the Internet of Things (IoT).

With 10 to 20 times faster speeds and dramatically lower latency, 5G makes it much more feasible to process AI workloads locally at the edge.

Hardware is about to get interesting again.

This speed and reduced latency is essential to an array of IoT applications such as smart cities, transportation, intelligent manufacturing, e-health, smart farming, and so on. This is why Gartner predicts that 75 percent of enterprise-generated data will be processed outside a traditional data center or cloud by 2022, compared with 10 percent today.

The powerful combination of NetCloud Edge Connector (https://aka.ms/iotshow/cradlepoint) and Microsoft Azure IoT Central enables customers to easily and confidently deploy IoT applications to drive business outcomes.

Optimizing operational efficiency, increasing customer satisfaction, and reducing CAPEX/OPEX for deployments are example benefits this solution can deliver.

NetCloud Edge Connector enables reliable and secure orchestration of IoT sensor data from Cradlepoint LTE edge routers to Microsoft Azure IoT Central. Now, Cradlepoint or Microsoft partners can easily build, deploy, and securely host IoT applications at scale for their customers driving IT/OT convergence.

Learn more reading Ken’s blog post at https://aka.ms/iotshow/cradlepoint

Barry Bond and Ryan Fairfax walk through the Azure Sphere OS architecture, why we chose a Linux kernel, and how the Azure Sphere OS is designed to offer unequaled security and agility for IoT devices and experiences.

Learn more visiting https://aka.ms/iotshow/azuresphere

Looking for a good DIY (Do It Yourself) IoT project?

There are so many interesting things that we can do with a few components and a little creatively.

In this video, Cam Soper comes on to show us how he automated his home with .NET Core, Hubitat, and Azure with his open source project called Puppet.

Time Index:

  • [01:00] – Taking a look at the setup
  • [02:29] – Triggering Hubitat events
  • [05:15] – Using .NET for interaction
  • [08:52] – The motivation behind Puppet
  • [13:35] – Running your own Puppet server

Useful Links