Types of Learning
Not every machine learns the same way. Some learn from examples with answers, some find patterns on their own, and some learn by trial and error. Meet the three big families: supervised, unsupervised and reinforcement learning.
New words
- Label
- The correct answer attached to an example.
- Supervised learning
- Learning from examples that come with correct answers.
- Unsupervised learning
- Learning from examples with no answers, by finding patterns.
- Clustering
- Putting similar items into groups without being told the groups.
- Reinforcement learning
- Learning by trying actions and getting rewards or penalties.
- Agent
- The program that tries actions and learns from rewards.
What you will learn
- Three ways to learn
- Supervised learning: learning with an answer key
- Unsupervised learning: finding groups on its own
- Reinforcement learning: trial, error and rewards
- Try it: all three, hands-on
- And what about ChatGPT?
- Where you see it every day
- Explain it to a friend
- Key takeaways
10 quiz questions at the end.
The full lesson, with interactive demos and the quiz, opens after you sign in with Google. It is free.