Skip to content

sgkiokas/taxinomitis

 
 

Repository files navigation

Machine Learning for Kids

What is this?

This is the source code for the API and website behind Machine Learning for Kids.

It's a tool aimed at children, which introduces machine learning by providing them with hands-on experiences for training simple machine learning systems and building things with them.

It provides an easy-to-use guided environment for training machine learning models for classifying text, numbers or recognising images.

This builds on existing efforts to introduce and teach coding to children, by adding these models to Scratch (a widely used educational coding platform), allowing children to create projects and build games with the machine learning models that they've trained.

It's currently running at https://MachineLearningForKids.co.uk

The code

This started as a personal side-project by Dale Lane for use by a couple of local schools. It's grown far beyond what I expected.

All of this is a long-winded way of saying that I never expected to share this code with anyone, let alone open-source it. It definitely has many of the embarrassing hallmarks of a hobby project tinkered with in evenings and weekends... please keep that in mind when you look through the code, and bear with me while I try and tidy things up.

The project worksheets

They are in a separate repository, so that they can be updated more frequently without re-deploying the application. They're all MS Word documents, so if you'd like to make improvements or even provide a new project worksheet, that would be fantastic.

They are managed in a separate repository. If you'd like to report a problem with one of the project worksheets, submit changes, or suggest or contribute a new project worksheet, please do that in the taxinomitis-docs repository.

About

Source code for Machine Learning for Kids site

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • TypeScript 66.4%
  • JavaScript 16.7%
  • HTML 14.9%
  • CSS 1.8%
  • Shell 0.2%