Machine Learning Basics
How machine learning works at a conceptual level: show the computer many examples, it finds patterns, then it makes predictions about new things; hands-on experience with Teachable Machine or similar tool
What a learner can do afterwards
- Describe the three steps of machine learning in simple terms (give examples, find patterns, make predictions)
- Train a simple model using a tool like Teachable Machine and describe what happened
- Explain why showing more and better examples makes the model more accurate
The lesson
You already know computers store information, and that you can sort things into groups by their patterns. Machine learning is a way of teaching a computer to spot a pattern by itself, instead of a person writing every single rule. It happens in three steps: show the computer lots of examples, let it find the pattern in those examples, then it can make a guess about something new it has never seen before.
Nora wants an app that can tell her sneakers apart from her rain boots. She uses a tool called Teachable Machine. First she shows it twenty photos of sneakers and twenty photos of rain boots, each one labeled. The tool studies the photos and finds the pattern: sneakers are low and bendy, rain boots are tall and stiff. Now when Nora holds up a brand new shoe, one the app has never seen, it guesses which kind it is.
More examples help, but so does variety. Photos of sneakers from different angles and in different light teach the true pattern better than the same photo copied many times.
Show examples, let the computer find the pattern, then it can predict about brand new things.
Watch it
Where it sits
Where this leads
Jobs that lean on this skill. Follow one to see everything it is built on.
8 questions wait behind this lesson, each with its answer explained. Every answer feeds the sky: stars light as they are learned, and dim when it is time to come back.