Learn about the recently launched Opinion Mining and Async offerings of Text Analytics.

From the video description:

In the first half, we will discuss how Opinion Mining (an extension of Sentiment Analysis) helps explore customers’ perception of aspects/opinions, such as specific attributes of products or services, in text. In the second half, we will learn about the new Async capabilities of Text Analytics, which will allow bundling various skills of Text Analytics and also allows large amount of text of up to 125K characters to be sent to Text Analytics via /analyze endpoint.

The next version of QnA Maker advances several core capabilities like better relevance and precise answering, by introducing state-of-art deep learning technologies. 

In addition, it also simplifies resource management by reducing the number of resources deployed.

The latest version will enable customers with strict geo requirements to deploy the service in the region of their choice end-to-end.

More Information:

PyTorch is one of the most popular open source machine learning framework that accelerates the path from research to production deployment.

In this tutorial, Dmytro Dzhulgakov, core contributor for PyTorch, will go through an introductory level hands-on tutorial for building fashion recognizer.

Related links:

Dictation in productivity apps such as Word empower people to conquer the blank page.

Dictating is a fast and easy way to get your thoughts on the page during brainstorming, outlining, and authoring content. Office voice commanding is the next step to make dictation more powerful.

Using AI powered by Microsoft Cognitive Services, Microsoft 365 users save time and effort with transcription and voice commanding. Office voice commanding is powered by Microsoft Cognitive services, including Cognitive Speech Studio and Language Understanding Cognitive Service.

Learn More:

ONNX Runtime inference engine is capable of executing ML models in different HW environments, taking advantage of the neural network acceleration capabilities.

Microsoft and Xilinx worked together to integrate ONNX Runtime with the VitisAI SW libraries for executing ONNX models in the Xilinx U250 FPGAs. We are happy to introduce the preview release of this capability today.

Video index:

[06:15] Demo by PeakSpeed for satellite imaging Orthorectification

Related links:

Other links:

Using data for machine learning and analytics can potentially expose private data. 

How can we leverage data while ensuring that private information remains private?

In this video, learn how differential privacy can be used to preserve privacy and get a demo on how you can use newly released open source system, WhiteNoise, to put DP into your applications.

Learn More: