# What is Meta-learning? Definition and meaning

Trains across many tasks so the model can adapt to a new one with very little data or few gradient steps.

## Definition

**Meta-learning**: Trains across many tasks so the model can adapt to a new one with very little data or few gradient steps.

In short: Learning how to learn new tasks quickly.

## When it is used

Fast adaptation, few-shot settings, and the idea behind in-context learners trained on many synthetic tasks.

## Where it fits

Meta-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.
- **[Self-supervised learning](/glossary/self-supervised-learning)**: Creates its own training signal by masking, corrupting or transforming the input and asking the model to recover or relate it.
- **[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.

## Learn more

The full guide to **[Meta-learning](/tools/meta-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: [Megatron-LM](/glossary/megatron-lm) · Next term: [Microservices](/glossary/microservices)
