---
title: 'Active learning'
description: 'A training loop in which the learner chooses which unlabeled examples should be sent to an oracle for labels.'
canonical_url: 'https://darkfactory.dev/glossary/active-learning'
markdown_url: 'https://darkfactory.dev/glossary/active-learning.md'
collection: glossary
date_published: '2026-08-04T00:00:00-04:00'
date_modified: '2026-08-26T00:00:00-04:00'
---

# Active learning


## Definition

Active learning is a supervised-learning loop in which the learner helps choose the next examples to label. The system scores unlabeled candidates with a query strategy, sends selected examples to an oracle such as a subject-matter expert, adds the answers to the training set, and repeats.

The aim is label efficiency. A useful query should provide more information than a randomly selected example, but usefulness depends on the strategy and the data. Uncertainty sampling asks for labels where the current model is least certain. Query by committee selects cases where several plausible models disagree. Other strategies seek coverage or expected error reduction.

## Early methods

H. Sebastian Seung, Manfred Opper, and Haim Sompolinsky introduced query by committee in 1992. David Cohn, Les Atlas, and Richard Ladner's 1994 paper used "active learning" in its title and formalized a related selective-sampling setup in which the learner controls where it receives information. These papers established influential methods, but they do not make every later use of the phrase refer to one algorithm.

## Distinguish it from nearby terms

Ordinary supervised learning accepts a labeled dataset as given. Active learning makes data selection part of the loop. It is not continual learning, which concerns updating a model as data or tasks change, and it is not reinforcement learning, where actions are learned from reward.

## Check your understanding

You have one million unlabeled medical images and budget for 2,000 specialist reviews. What would your query strategy select, who acts as the oracle, and how would you test whether the selected cases improve the model more than random sampling?

## Related terms

- [Dataset](https://darkfactory.dev/glossary/dataset)
- [Label](https://darkfactory.dev/glossary/label)
- [Supervised learning](https://darkfactory.dev/glossary/supervised-learning)

## Evidence and further reading

- [Google Machine Learning Glossary](https://developers.google.com/machine-learning/glossary/)
- [Query by Committee](https://doi.org/10.1145/130385.130417)
- [Improving Generalization with Active Learning](https://doi.org/10.1007/BF00993277)