Tool That Introduces Children to Machine Learning and Its Real-World Applications

Machine learning (ML) is all around us. We all use machine learning systems every day—such as spam filters, recommendation engines, language translation services, chatbots and digital assistants, search engines, and fraud detection systems. It will soon be normal for machine learning systems to drive our cars and help doctors diagnose and treat our illnesses.

Machine Learning for Kids is a useful tool for introducing youth to how ML systems are trained and how they are used, along with some of the real-world implications of artificial intelligence applications.

The tool is entirely web-based and requires no installation or complicated setup. It was designed for use in the classroom by schools and volunteer-run coding groups for youth. An administrator page lets teachers or group leaders manage children’s access and work.

In this easy-to-use guided environment, youngsters can train machine learning models to recognize text, numbers, images, or sounds. The tool builds on existing efforts to introduce and teach coding to children by adding these models to the educational coding platforms Scratch and EduBlocks, and then by helping them create projects and build games with the machine learning models they train.

Pretrained models are also available for youth to use in building their projects. These advanced models enable projects that might otherwise be too complex for children to train on their own.

Share this post: