Dancing with AI

Dancing with AI is a week-long workshop curriculum in which students conceptualize, design, build, and reflect on interactive physical-movement-based multimedia experiences.

The curriculum is focused on designing interactions, training and evaluating AI models. Students will learn to build interactive AI projects using two new Scratch Extension tools developed for this curriculum:

• Hand/body/face position-tracking and expression-detecting blocks based on the machine learning models PoseNet & MediaPipe from Google and Affectiva’s face model, 
• Teachable Machine blocks that allow students to train their own image- and pose-recognition models on Google’s Teachable Machine and use them as part of their projects.

The content is structured as a 5-day workshop(2-3 hours per day). Course resources include teacher slides, teacher facilitation guides, students journal etc.

Dancing with AI was created by the Personal Robots Group at the MIT Media Lab