IBL News | New York
edX, HarvardX, and Google’s TensorFlow Open Source Machine Learning Platform yesterday announced the TinyML Professional Certificate program, scheduled to be launched in Fall 2020.
Tiny Machine Learning (TinyML) is an emerging field in the intersection of embedded machine learning (ML) applications, algorithms, hardware, and software. It requires software and embedded-hardware expertise.
This first-of-its-kind program will emphasize hands-on experience with ML training and deployment in tiny microcontroller-based devices.
The course features projects based on a TinyML program kit that includes an Arm Cortex-M4 microcontroller with onboard sensors, a camera, and a breadboard with wires—enough to unlock capabilities such as image, sound, and gesture detection.
The course will also feature real-world application case studies, guided by industry leaders, that examine the challenges facing real-world TinyML deployments.
Learners will be able to build a TensorFlow model using Python in Colab, then convert it to run in C on a microcontroller. The course will show how to optimize the ML models for severely resource-constrained devices (e.g., those with less than 100 KB of storage). Also, it will include various case studies that examine the challenges of deploying TinyML “into the wild.”