Demystifying AI · Stage 6

Kinds of machine learning

โ† Demystifying AIStage 6: Using AI wellNot yet checked by our team

Supervised learning learns from labelled examples (this email is spam, this photo is a cat) and predicts labels for new ones. Unsupervised learning gets no labels and finds structure by itself, such as groups of customers with similar habits. Reinforcement learning learns by trial and error from rewards, like a program that learns a game. Large language models are pre-trained by predicting the next word in huge amounts of text, which needs no hand-made labels (often called self-supervised), then tuned further with human feedback.

Why it matters: Choosing the right kind of learning is the first question in any AI project.

Builds on: Learning from examples

Learn it, then prove it

Sign in (free) to take this step's mastery check and save your journey.


Contact Us

Questions or feedback about anything? We'd love to hear from you.

You can reach us at: support@seriousmindware.com