This article was originally posted in the Microsoft Azure blog.
We are seeing a clear trend towards a future powered by the intelligent cloud and intelligent edge. The intelligent cloud is ubiquitous computing at massive scale, enabled by the public cloud and powered by AI, for every type of application one can envision. The intelligent edge is a continually expanding set of connected systems and devices that gather and analyze data—close to end users and the data that is generated. Together, they give customers the ability to create a new class of distributed, connected applications that enable breakthrough business outcomes.
To accelerate this trend, today we are announcing the preview of Azure Cognitive Services containers, making it possible to build intelligent applications that span the cloud and the edge. Azure Cognitive Services allow developers to easily add cognitive features—such as object detection, vision recognition, and language understanding—into their applications without having direct AI or data science skills or knowledge. Over 1.2 million developers have discovered and tried Azure Cognitive Services to build and run intelligent applications. Containerization is an approach to software distribution in which an application or service is packaged so that it can be deployed in a container host with little or no modification.
With container support, customers can use Azure’s intelligent Cognitive Services capabilities, wherever the data resides. This means customers can perform facial recognition, OCR, or text analytics operations without sending their content to the cloud. Their intelligent apps are portable and scale with greater consistency whether they run on the edge or in Azure.
Run AI on the edge
With ever-increasing volumes of data being generated across organizations, customers have been asking for the flexibility to deploy AI capabilities in a variety of environments. By deploying Cognitive Services in containers, customers can analyze information close to the physical world where the data resides, to deliver real-time insights and immersive experiences that are highly responsive and contextually aware. Cognitive Services containers that customers deploy on their own premises do not send customer data (e.g., the image or text that is being analyzed) to Microsoft.
Build consistent app architectures across the cloud and edge
Cognitive Services containers enable customers to build one application architecture that is optimized to take advantage of both robust cloud capabilities and edge locality. With containers, customers can choose when to upgrade the AI models deployed in their solutions. Customers can also test new model versions before deploying them in production in a consistent way, whether running on the edge or in Azure.
Customers and partners are already taking advantage of these enhanced capabilities to drive their businesses forward.
Psiori is using Cognitive Services containers to analyze medical documents such as lab reports and images directly on the edge to automate and streamline insurance reimbursements. “We were eager to find a solution that gives us high-quality AI; but could also maintain our compliance boundary onsite at local hospitals and the Cognitive Services support for containers was exactly what we were looking for,” said Jona Boddinghaus, partner and senior software developer at Psiori.
Avanade, a global professional services company, is using Cognitive Services containers to build new intelligent edge applications for their customers where connectivity is constrained. “The areas I see containers and Cognitive Services alleviating customer friction points are when there’s a semi-disconnected environment such as on remote oil rigs, or ships in the middle of the ocean or factory floors,” said Amit Bahree, CTO for AI at Avanade.
Intel is working on hardware solutions that deliver security for Linux containers. “Azure Cognitive Services containers give you more options on how you grow and deploy AI solutions, either on or off premises, with consistent performance. You can scale up as workload intensity increases or scale out to the edge,” said Andy Vargas, Intel VP of Software and Services.
Get started today!
Take advantage of Azure Cognitive Services containers to build intelligent applications today. For more details, please see the technical blog, “Getting started with Azure Cognitive Services in containers”.
To learn more about our edge solutions, please see Julia White’s edge computing blog.