SantageAI Glossary › Supervised Learning
AI Glossary

What is Supervised Learning?

Supervised learning is a type of machine learning in which a model learns from labelled examples, mapping inputs to known correct outputs.

What is the core idea behind supervised learning?

Supervised learning learns from an answer key, generalising from labelled examples to new data.

How does supervised learning differ from related concepts?

ConceptDifference
Supervised vs Unsupervised LearningSupervised learning uses labelled data. Unsupervised learning finds structure in unlabelled data.
Supervised vs Reinforcement LearningSupervised learning learns from correct answers. Reinforcement learning learns from rewards for actions.
Supervised vs Semi-SupervisedSemi-supervised learning mixes a small labelled set with a large unlabelled one to cut labelling cost.

How does supervised learning work?

What are common supervised learning tasks?

Why is supervised learning important?

Supervised learning is the most widely used form of machine learning in production, because labelled data maps directly to clear business tasks. Most classification and prediction systems in industry rely on it.

How is supervised learning used in practice?

It is used in email spam filters, credit scoring, medical diagnosis, image classification, and demand forecasting. Its main constraint is the need for large amounts of accurately labelled data, which is expensive to produce.

Frequently Asked Questions

What is the difference between supervised and unsupervised learning?
Supervised learning trains on labelled examples with known answers. Unsupervised learning works on unlabelled data to discover hidden patterns or groupings.
Do large language models use supervised learning?
Partly. Their pre-training is self-supervised, but supervised fine-tuning on labelled examples is a key step in making them follow instructions.