Creative Technologists Lucas Ochoa and Gautam Bose of Google Creative Lab conducted a yummy experiment with an AI sorting machine that separated the marshmallows parts of Lucky Charms cereal from the cereal itself.
This fun experiment was also a demonstration of how Google’s Teachable Machine paired with the Coral USB Accelerator can be used to create a machine that can be taught to recognize and sort objects using custom machine learning models.
This project shows you how to build a machine to classify and sort objects. It leverages Teachable Machine, a web-based tool that lets you easily train your own image classification model without writing any code, and then uses the Coral USB Accelerator for inferencing based on that model to classify and sort objects.
via The Awesomer