Plain-AyI
← All projects
Learning resources

Have Fun with Machine Learning

A hands-on beginner's guide to training an AI that tells dolphins from seahorses in photos.

New this week

What it does

This guide teaches programmers with no AI background how to use machine learning in practice. The goal is to train a neural network that recognizes whether a photo shows a dolphin or a seahorse.

It covers building an image dataset, training a model from scratch, improving it by adapting existing models, and testing it on new pictures. It skips theory and maths on purpose. It uses older tools (Caffe and NVIDIA DIGITS), and is available in English, Chinese and Korean.

Who it's for

Programmers curious about machine learning who want a friendly, practical first project.

Can I use it without coding?

Yes. Reading is free; following along needs some technical setup. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Web browser
Computer
An ordinary computer is fine
API key
Not needed

Try it

  1. Read the guide on the project page from the beginning.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it