AI Glossary Term

What does “Supervised Learning” mean?

Definition

Training a model with labeled examples that map inputs to known outputs.

Browse the full AI Glossary Explore all free AI guides

How Supervised Learning works

Example

To predict house prices, you give the model thousands of past sales with their actual prices. It learns the link between features and price and then estimates the price of a house it has not seen.

Why it matters

It is the most common form of machine learning in business. It needs good labels, which can be costly to get.

Common questions

Two main tasks?

Classification (predict a category) and regression (predict a number).

Where do labels come from?

People, records of past outcomes, or measurements.

Supervised vs unsupervised?

Supervised uses labeled answers; unsupervised looks for structure without them.

Safety FilterA moderation layer that blocks or rewrites unsafe model inputs or outputs.Data AugmentationTechniques that create modified training examples to improve model generalization.Data LabelingThe process of assigning tags or target outputs to raw data for supervised learning.DatasetA collection of structured or unstructured examples used for training, validation, or testing.Knowledge DistillationTraining a smaller model to imitate the outputs of a larger model.OverfittingWhen a model memorizes training data and performs poorly on unseen inputs.

Learn more in our free guides

Deep Learning Reinforcement Learning Machine Learning Basics Supervised Learning

Test yourself

Deep Learning Quiz Reinforcement Learning Quiz Machine Learning Basics Quiz