The Embedded Learning Library (ELL) allows you to build and deploy machine-learned pipelines onto embedded platforms, like Raspberry Pis, Arduinos, micro:bits, and other microcontrollers. The deployed machine learning model runs on the device, disconnected from the cloud. Our APIs can be used either from C++ or Python.

This project has been developed by a team of researchers at Microsoft Research. It's a work in progress, and we expect it to change rapidly, including breaking API changes. Despite this code churn, we welcome you to try it and give us feedback!

A good place to start is the tutorial, which allows you to do image recognition on a Raspberry Pi with a web cam, disconnected from the cloud. The software you deploy to the Pi will recognize a variety of common objects on camera and print a label for the recognized object on the Pi's screen.

See LICENSE.txt.

This project has adopted the Microsoft Open Source Code of Conduct. For more information on this code of conduct, see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

• On Windows
• On Ubuntu Linux
• On Mac OS X

• Design overview of data library
• Design overview of math library
• Design overview of model and nodes libraries
• Definition of the generalized sparse data format
• Description of the training algorithms implemented in trainers