AI with Finch

Train machine learning models to have your Finch react to speech, images, pose, and drawings!

ADVANCED: Going Further

The following hands-on activities are designed to enable you to create and test your own machine learning models. The first three activities use Google Teachable Machine to create machine learning models that you can incorporate into your Snap! programs. These models are quick to create online but will enable you to develop some intuition for how machine learning works and how it depends on the data that you use to create it. There are three types of machine learning models that you can create: image recognition, audio recognition, and pose recognition. You will find an activity for each below. In each activity, you will create and test a machine learning model and then use it in a Snap! program.

In Activity 4, you will create your own machine learning model. The mathematics behind such models can be very complicated, but this activity will use a simplified model to give you an idea of what is happening “behind the scenes” in machine learning.

Activity 1: Image Recognition

Activity 2: Audio Recognition

Activity 3: Pose Recognition

Activity 4: Sketch Recognition