J2021 is a hand-size edge AI box built with Jetson Xavier NX 8GB module which delivers up to 21 TOPs AI performance, rich set of IOs including USB 3.1 ports(4x), M.2 key E for WIFI, M.2 Key M for SSD, RTC, CAN, Raspberry Pi GPIO 40-pin, and so on, aluminum case, cooling fan, pre-installed JetPack System, as NVIDIA Jetson Xavier NX Dev Kit alternative, ready for your next AI application development and deployment The full system includes the same form factor carrier board as the Jetson NX Developer Kit, one Jetson Xavier NX production module, a heatsink, and a power adapter. New Arrival: If you are looking for a full system that comes with industrial communications such as RS232/RS485. Please check our new industrial A203 and A205- E mini PCs, with pre-installed Jetpack 5.0.2, 128GB SSD, and WIFI/BT module, as also industrial interfaces. You can train a brand new custom model just in hours, or you can even use choose one of 130 pre-trained models from the always dashboard, deploy it to edge devices, and build a computer vision application within minutes! With an extensive library of Python APIs, you can also customize any AI application, and also push real-time analytics to platforms such as Data Lakes and BI tools for further data visualization.

Containers have become the unit of deployment not just for data center and cloud workloads but also for edge applications. Along with containers, Kubernetes has become the foundation of the infrastructure. Distributions such as K3s are fueling the adoption of Kubernetes at the edge. I have seen many challenges when working with large retailers and system integrators rolling out Kubernetes-based edge infrastructure. One of them is the ability to mix and match ARM64 and AMD64 devices to run AI workloads.

SMARC based platforms based on the NXP i.MX 8M Plus processors are an ideal fit for embedded AI applications. Equipped with an extensive ecosystem with application-ready 3.5-inch carrier board, Basler cameras, and AI software stack, fast proof of concept is possible says Martin Danzer Loncaric is director of product management at congatec AG. Implementing Arm technology hasn't always been so easy. Previously, it was usually much more difficult to use the latest processor technology from the Arm environment as a finished system than to implement the x86 environment. However, with a modular approach based on the SMARC computer-on-modules specification, it is now also possible to obtain standard form factors from the x86 box PC range with ARM processors.

Azure Percept is the latest edge computing platform from Microsoft. Announced at the recent Ignite event, the platform brings the best hardware, software and cloud services to the edge. Azure Percept is an exciting device for makers and builders to build and prototype intelligent IoT applications powered by Azure Cognitive Services and Azure Machine Learning Services. The Azure Percept platform has three elements - the hardware, development kit, and cloud-based development and management tools. Microsoft is working with the ecosystem of hardware developers to publish patterns and best practices for developing edge AI hardware that can be integrated easily with Azure AI and IoT services.

Objective: Deep learning-based neural decoders have emerged as the prominent approach to enable dexterous and intuitive control of neuroprosthetic hands. Yet few studies have materialized the use of deep learning in clinical settings due to its high computational requirements. Methods: Recent advancements of edge computing devices bring the potential to alleviate this problem. Here we present the implementation of a neuroprosthetic hand with embedded deep learning-based control. The neural decoder is designed based on the recurrent neural network (RNN) architecture and deployed on the NVIDIA Jetson Nano - a compacted yet powerful edge computing platform for deep learning inference. This enables the implementation of the neuroprosthetic hand as a portable and self-contained unit with real-time control of individual finger movements. Results: The proposed system is evaluated on a transradial amputee using peripheral nerve signals (ENG) with implanted intrafascicular microelectrodes. The experiment results demonstrate the system's capabilities of providing robust, high-accuracy (95-99%) and low-latency (50-120 msec) control of individual finger movements in various laboratory and real-world environments. Conclusion: Modern edge computing platforms enable the effective use of deep learning-based neural decoders for neuroprosthesis control as an autonomous system. Significance: This work helps pioneer the deployment of deep neural networks in clinical applications underlying a new class of wearable biomedical devices with embedded artificial intelligence.

When opportunity knocks, open the door: No one has taken heed of that adage like Nvidia, which has transformed itself from a company focused on catering to the needs of video gamers to one at the heart of the artificial-intelligence revolution. In 2001, no one predicted that the same processor architecture developed to draw realistic explosions in 3D would be just the thing to power a renaissance in deep learning. But when Nvidia realized that academics were gobbling up its graphics cards, it responded, supporting researchers with the launch of the CUDA parallel computing software framework in 2006. Since then, Nvidia has been a big player in the world of high-end embedded AI applications, where teams of highly trained (and paid) engineers have used its hardware for things like autonomous vehicles. Now the company claims to be making it easy for even hobbyists to use embedded machine learning, with its US $100 Jetson Nano dev kit, which was originally launched in early 2019 and rereleased this March with several upgrades.

The advances made over the last few years in the field of artificial intelligence (AI) are allowing this technology to permeate into all areas of industry, creating "smart" applications and even smart industries. This revolution has created the AIoT, which is a morphing of AI and IoT. You could make an argument that the previous winners of the IoT explosion were the sensor makers and the Cloud providers. The latter were especially successful in that it was the keeper of the data--more data than most individuals could wrap their arms around. The next step, which was taken by most Cloud vendors, was to provide analytics to its customers: "You have all this data. Now you need to make use of it."

Luxonis' $99, Intel Myriad X based "DepthAI" module for robotics is available on CrowdSupply along with DepthAI-based Raspberry Pi HAT, USB adapter, and RPi CM3 B equipped boards. DepthAI provides up to 25.5 fps object detection. Luxonis has gone to Crowd Supply to pitch a neural accelerator module for the Raspberry Pi based on the up to 4-TOPs Movidius Myriad X Vision Processor Unit (VPU). The company claims its DepthAI can offload far more processing from the Raspberry Pi than a Pi mated with Intel's Myriad X based Intel Neural Compute Stick 2 (NCS2) USB stick accelerator. That's particularly notable since Intel owns Movidius.

Organizations in all industries are looking for ways to capitalize on technology megatrends like AI, machine learning and the IoT. More than just increasing efficiency and reducing costs, these enabling technologies allow for the implementation of new applications, services and revenue models. However, many of the electronic systems in operation today are typically deployed for five years, 10 years, or longer, which makes it difficult for OEMs and system integrators to capitalize on new advancements in technology. In fact, in this time of rapid innovation, the mere presence of legacy electronic systems can accelerate technical and business obsolescence. Such is the case in sectors like industrial automation, health care, and test & measurement, where many electronic systems have been designed around integrated architectures.