CACrown ArchivesThe cinema collection
EN/FR
Search
Menu
Research dossier · General Reference

Meta-learning (computer science)

Subfield of machine learning

Cross-disciplinary reference desk with index cards, atlas, dictionary and catalogue
General referenceInterpretive dossier study · Crown Archives visual atlas
Record originEnglish Wikipedia
Text licenseCC BY-SA 4.0
Source revisionJul 22, 2026
Entity authoritySource title only
Source-derived summary

Meta-learning

is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017, the term had not found a standard interpretation, however the main goal is to use such metadata to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself, hence the alternative term learning to learn.

Editorial summary

The public source identifies “Meta-learning (computer science)” as subfield of machine learning. This brief keeps that definition visible, then builds a research path around Meta-learning, computer and science.

Editorial reviewA dependable orientation record for establishing vocabulary, names and a first evidence trail. The current lead gives the account dated anchors—2017—that can be checked directly. The selected authority fields contribute no independent date. Its value is orientation rather than verdict, with Meta-learning, computer and science providing the first useful test.
Editorial analysis

Why this record matters

A short description can identify a subject without explaining its stakes. For “Meta-learning (computer science)”, the useful work is to connect “subfield of machine learning” to the records capable of establishing context and consequence.

Evidence profile

Named sources, stable identifiers and responsible institutions provide the strongest route from overview to verifiable evidence. The source revision retrieved here is dated Jul 22, 2026. The first chronological checks are 2017.

Critical limits

Overview language is designed for orientation and should not be treated as a substitute for the evidence cited beneath it. The source lead contains qualifying language; that uncertainty should survive quotation, summary and reuse. Authority statements aid reconciliation but still require their own references, qualifiers and ranks to be checked.

How to read it

Use the entry as an orientation point, then follow its citations and revision history. Names, dates and institutional relationships should be checked against the original record.

Best used for
  • Subject orientation
  • Search vocabulary
  • Locating named sources
Verify next

The closest primary source, responsible institution and strongest cited specialist reference.

Three-step research path

  1. Establish the record: confirm the title “Meta-learning (computer science)”, its source revision and the description used here.
  2. Expand the search: follow Meta-learning (computer science) primary sources, Meta-learning (computer science) archive and Meta-learning research across catalogues and specialist indexes.
  3. Test the account: compare the strongest cited source with the responsible institution’s current record and note any disagreement.

Questions for further research

  1. Which source most directly establishes the central claim about “Meta-learning (computer science)”?
  2. Which cited source is closest to the event, object or claim?
  3. Which institution is responsible for the underlying evidence?
Subject index

Search terms from this dossier

Source & attribution

This entry incorporates text from “Meta-learning (computer science)” on English Wikipedia. Contributors are listed in the page history. Text is available under the Creative Commons Attribution-ShareAlike 4.0 License. Selected authority identifiers and statements are retrieved from Wikidata under CC0; their references and qualifiers remain part of the verification path.