Machine Learning Basics
A basic explanation of machine learning: a computer studies many examples, finds patterns and makes predictions about new things. Includes hands-on practice with Teachable Machine or a 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 how relevant, varied examples can help a model and why its guesses still need testing
1 · Read
You have sorted things by a rule. Machine learning lets a computer learn patterns from examples. People write the learning software. For our picture sorter, first give labeled examples, then train it to find clues that separate the groups. Next, try a new picture and check its guess. A guess is called a prediction.
Nora uses Teachable Machine to sort sneakers and rain boots. She supplies labeled photos, selects Train, then checks new photos. A guess matching the known label is correct; a different label is a mistake. The model might use shape or background clues. To compare results, subtract the smaller number of correct guesses from the larger: 8 minus 6 is 2 more.
Useful examples show different shoes, angles, light and backgrounds. Repeating one photo adds little variety. If boot photos are rainy and sneaker photos are dry, a model may learn rain as a clue. Show both kinds in different weather. More relevant, varied examples can help, but test new pictures to find out.
Give examples, train the model, then check its guesses on new examples. Relevant variety can help it learn useful patterns.
2 · Watch
Take it off screen
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.