The Silicon Review ^Asia

Microsoft has recently declared its AI Platform that will help Windows developers to bring the machine learning models trained in the cloud to desktop apps. The new set of tools in Windows 10 is supposed to be launched with the next major version of Windows.

The AI Platform will utilize the GPU on the local machine and enable developers to run their models in real time without accessing and moving them to the cloud. According to Kam VedBrat, Microsoft Partner Group program manager, what the company is building really completes the story for Microsoft from an AI perspective. Earlier, Microsoft had mentioned about its machine learning infrastructure in the cloud and the tooling built around this. This helps developers build their models in the cloud according to their frameworks and then integrate these models with their desktop apps using Visual Studio.

Onnx, a project backed by Microsoft, Facebook and Amazon, is at the core of this. This also allows developers to convert Caffe2, PyTorch, CNTK and other models into the Onnx format to move them between frameworks as necessary. From the next preview of Visual Studio 15.7, developers can simply add an ONNX file to their Universal Windows Platform (UWP) apps and Visual Studio will generate a model interface for the project. The tooling for previous versions of Visual Studio will also be made, and Microsoft will add this capability to the Visual Studio tools for AI.