# What is Self-supervised learning? Definition and meaning

Creates its own training signal by masking, corrupting or transforming the input and asking the model to recover or relate it.

## Definition

**Self-supervised learning**: Creates its own training signal by masking, corrupting or transforming the input and asking the model to recover or relate it.

In short: Learning from the data itself by hiding parts and predicting them.

## When it is used

Pre-training foundation models on unlabelled text, images and tables, before any task-specific labels are used.

## Where it fits

Self-supervised learning belongs to **Learning paradigms** in the [Machine learning](/topics/machine-learning) topic. These are the other terms in the same group:

- **[Supervised learning](/glossary/supervised-learning)**: A learning setup where every training example comes with the correct answer, and the model learns the mapping from inputs to that answer.
- **[Unsupervised learning](/glossary/unsupervised-learning)**: Learning from data without target labels, by discovering clusters, directions of variation, or density.
- **[Semi-supervised learning](/glossary/semi-supervised-learning)**: Training with a small labelled set and a much larger unlabelled set, so that the unlabelled data shapes the decision boundary.
- **[Reinforcement learning](/glossary/reinforcement-learning)**: An agent acts in an environment, receives rewards, and learns a policy that maximizes long-term reward.
- **[Transfer learning](/glossary/transfer-learning)**: Starts from weights learned on a large source task and adapts them to a smaller target task.
- **[Few-shot learning](/glossary/few-shot-learning)**: Adapts a model to a new task using only a few labelled examples, often through in-context examples or small updates.
- **[Zero-shot learning](/glossary/zero-shot-learning)**: The model solves a task it was never explicitly trained on, relying on general knowledge and a task description.
- **[Meta-learning](/glossary/meta-learning)**: Trains across many tasks so the model can adapt to a new one with very little data or few gradient steps.

## Learn more

The full guide to **[Self-supervised learning](/tools/self-supervised-learning)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [scikit-learn](/glossary/scikit-learn) · Next term: [Semantic sector heads](/glossary/semantic-sector-heads)
