Build a Teachable Machine Image Classifier With Your Kid

A hands-on, zero-cost weekend project to teach children ages 8 to 16 how computer vision models actually learn.

Artificial intelligence can feel like magic to a child. To prepare them for the future, we must demystify the technology and show them that AI is simply a tool that learns from patterns.

This weekend project allows you and your child to build, train, and test a real machine learning model. Using household items, a standard laptop webcam, and a free web tool, your child will step into the role of an AI engineer. They will build a system that can instantly distinguish between different objects, such as a favorite toy, a book, or hand gestures.

The Power of Hands-On AI Education

Reading about AI or watching videos does not build true technological literacy. Children learn best by doing. When they actively train a model, they see the direct relationship between the data they provide and the decisions the computer makes.

This project uses Google's Teachable Machine, a free, web-based tool that requires no coding, no registration, and no paid subscriptions. It runs entirely in the browser, making it safe, private, and highly accessible.

Step 1: Set Up Your AI Lab

Before starting, gather your materials. You will need:

• A laptop or desktop computer with a working webcam.
• Two or three distinct objects from around the house (for example, a blue pen and a red apple, or a Lego figure and a toy car).
• A well-lit room to ensure the camera captures clear images.

Once gathered, open your web browser and navigate directly to the Teachable Machine Website . Click on "Get Started" and select "Image Project," then choose the "Standard Image Model."

Step 2: Define and Train Your Classes

In machine learning, a "class" is a category of data. You will train your model to recognize these categories.

• Name Your Classes: Rename "Class 1" to the name of your first object (e.g., "Lego Brick"). Rename "Class 2" to your second object (e.g., "Toy Car").
• Record Training Images: Click the webcam button under Class 1. Hold your first object in front of the camera. Click and hold the "Record" button to capture at least 100 images. Encourage your child to rotate the object, move it closer and further away, and tilt it. This variety helps the model learn the object's shape from different angles.
• Record the Second Class: Repeat the process for Class 2 with your second object, capturing a similar number of images.
• Train the Model: Click the "Train Model" button. Keep the browser tab open and active. Within a few seconds, the computer will process the images and find the patterns that distinguish the two objects.

Step 3: Test and Break the Model

Once training is complete, the "Preview" panel on the right will activate, showing a live feed from your webcam.

Have your child hold up the first object. The model should show a high confidence percentage (near 100 percent) for Class 1. Now, hold up the second object and watch the percentage shift to Class 2.

Now comes the most educational part: try to trick the model. What happens if you hold up a completely different object? What happens if you hide half of the toy car behind your hand? What happens if you turn off the lights? This experimentation helps children understand that the model does not actually "know" what a car is; it only recognizes the pixels and patterns it was trained on.

Parent & Educator Sidebar

Core AI Concept: Supervised Learning Supervised learning is a type of machine learning where the computer is trained using labeled data. In this project, the labels are the class names, and the data is the set of webcam images. The computer looks for common features (colors, edges, shapes) in each class to build its classification rules.

Conversation Starters:

• "Why do you think the computer got confused when we turned off the lights or changed the background?"
• "How could we make this model smart enough to recognize the toy even in a dark room?"
• "How do you think self-driving cars use this exact technology when they are driving down a busy street?"

Action Steps Summary

• Open the Tool: Go to the Teachable Machine Website on a laptop.
• Gather Objects: Select two distinct household items to classify.
• Capture and Train: Record 100 images for each object from various angles, then click "Train."
• Test and Discuss: Try to trick the model and use the sidebar questions to discuss how machine learning works.

Want more engaging, family-friendly AI projects and guides?