Catching the carpool cheats

I’ve added a new project worksheet to Machine Learning for Kids, based on the idea of a traffic camera in a carpool lane.

Students create training examples by labelling pictures of cars with random passengers in.

recording of creating the training examples at

This will result in a collection of images ready for training a machine learning model.

screenshot of the training data

They then use their machine learning model to power a carpool game.

In this game, students control the cars. Each lane has a different speed limit, and they get points for each car that reaches the end of the road.

If they use the carpool lane in a car without any passengers, their machine learning-powered traffic camera will fine them – deducting points from their score.

recording of the carpool game at

It’s a fun and simple project – and makes a quick demo of how computers can learn to recognize details in images.

If you’d like to give the project a try, you can download a PDF with the instructions from the worksheets tab on Machine Learning for Kids.

Tags: ,

Leave a Reply