Patterns and Classification
Humans are great at spotting patterns; computers can learn to spot patterns too, but they need lots of examples; sorting and classification activities as the basis of machine learning
What a learner can do afterwards
- Sort a set of items into categories and explain the rules they used
- Explain that computers learn patterns by looking at many examples
- Describe why a computer needs more examples than a human to learn the same pattern
The lesson
You are already great at spotting patterns. If you saw a pile of red and blue blocks, you could sort them by color in seconds, without anyone teaching you the rule first.
Priya has a box of buttons, some round and some square. She makes two piles: round buttons in one, square buttons in the other. When you ask her why, she says, 'Round ones together, square ones together.' That is her rule.
Computers can learn to sort things too, but they do not start out knowing any rules. To learn what a cat looks like, a computer studies many pictures labeled 'cat' or 'not cat' until it notices what cats have in common.
A person might only need to see a few cats to know what a cat looks like. A computer usually needs hundreds or thousands of labeled pictures, because it does not understand the world the way you do.
Sorting things by a shared rule is classification, and it is exactly how computers learn patterns too, just with far more examples.
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.