Learn AI · Level 2 · How AI works · step 3 of 16 · word 1 of 5
What is supervised learning?
Supervised learning trains a model on examples that come with the right answer attached, like photos labelled "cat" or "dog", so it learns to label new ones.
In plain English
It is learning with an answer key. You show the model thousands of examples, each with its correct label. It guesses, checks against the label, adjusts, and tries again, until it gets new examples right on its own.
An example
A spam filter learns from emails that people have already marked “spam” or “not spam”. After enough examples it can sort new emails it has never seen.
Watch out
Labels are made by people, so they take time and money, and they can be wrong or biased. A model learns the labels’ mistakes too. Compare unsupervised and self-supervised learning, which need no labels.
Learn AI path · Level 2 · How AI works · step 3 of 16
Next wordUnsupervised learning →See all of level 2