Skip to content
Smartable Academy
Smartable tools

← Meeting AI: What It Is and What It Isn't

Your progress

Checking your sign-in…

Who's learning?

Each profile keeps its own read lessons, badges, streak, and practice scores on this device.

Lesson 4 of 8

Three ways a machine can learn

Show on a big screen

5 min

Text size

An AI learns from data, the examples it is given. It can learn in three ways.

Supervised: photos already labelled ripe or unripe.
Step 1 of 3
  1. Supervised: photos already labelled ripe or unripe.
  2. Unsupervised: photos with no labels. It finds its own groups.
  3. Reinforcement: it tries, gets a score, tries again.

Supervised learning has labels. Unsupervised has none. Reinforcement learns from rewards.

A label is the right answer on an example. Some data has labels. Some has none. Without labels, an AI finds groups by itself. With rewards, an AI gets a score for a good try.

Read each case. Pick the way of learning.

Loading lab…

Try the lab to finish this lesson.