How about designing and deploying intelligent machine-learned models onto resource constrained platforms and small single-board computers, like Raspberry Pi, Arduino, and micro:bit? How cool would that be?

This is exactly what the open source Embedded Learning Library (ELL) project is about. The deployed models run locally, without requiring a network connection and without relying on servers in the cloud. ELL is an early preview of the embedded AI and machine learning technologies developed at Microsoft Research.

Chris Lovett from Microsoft Research gives us a fantastic demo of the project in this episode of the IoT Show.

Get the ELL code on GitHub:

In this episode of Visual Studio Toolbox, Robert Green talks to Sam Basu about what it takes to build a bot.

A bot is software that interacts with humans to do things like chat, make recommendations, book travel and more. This is the first of a two part series where Sam Basu shows us how to build bots. What are the tools we use and how do they work? Once you understand that, you can think about how you can use them in ways that help your customers. 

Anna Thomas has been collecting notes for the past two years from field members (internal and external) who have developed complex LUIS models. In this video, learn some of the limitations or challenges that are faced when you try to deploy enterprise-ready LUIS models at scale, and how they can be addressed.

The related blog post can be found at The related video on botbuilder-tools is here.