Microsoft’s Windows ML platform is now generally available for production use, making it easier for developers to add AI to their Windows apps. In its announcement blog, Microsoft says Windows ML is supported on all devices running Windows 11 24H2 or newer, and provides a local AI inference framework that helps to build more “responsive, private, and cost-effective” AI experiences.
“The way this works is silicon partners build and maintain execution providers that Windows ML distributes, manages, and registers to run AI workloads performantly on-device, serving as a hardware abstraction layer for developers and a way to get optimal performance for each specific silicon,” Microsoft says in the announcement. In simple terms, the platform enables AI-infused apps to tap into PC hardware that’s best suited for their specific workload, such as GPUs for power-intensive tasks, NPUs for power efficiency, and CPUs for flexibility.
Windows ML has been in development for several years, having first been unveiled for Microsoft’s Windows 10 operating system in 2018. Microsoft says that software developers, including Adobe, McAfee, and Topaz Labs are now working on adopting Windows ML in their upcoming releases after helping to test the platform during its development.
The upcoming integration for Adobe’s Premiere Pro and After Effects video editing software will harness local NPUs for semantic search, audio tagging, and scene edit detection features. McAfee is also using Windows ML to automatically detect deepfake videos and scams on social networks, and Topaz Labs utilized the platform to develop AI-powered image editing features in Topaz Photo. With Windows ML streamlining AI development in Windows-based apps, Microsoft is hoping for an influx of similar AI experiences that can entice more consumers to its operating system.
Read the full article here
