Metraipolis › archive › dc_69a631973e43

Zero-Shot Learning — Wikipedia (de)

Source
Wikipedia (de)
Original
https://de.wikipedia.org/wiki/Zero-Shot_Learning
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-06T10:51:34.249Z
SHA-256 of the archived text
ff12c6ac294425db6c0dce834d3951150fa80ffb1b25575d85cf920c7fb06485
Stable URL of this page
https://metraipolis.com/documento/dc_69a631973e43

How to cite

Zero-Shot Learning — Wikipedia (de) — Wikipedia (de), https://de.wikipedia.org/wiki/Zero-Shot_Learning (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_69a631973e43 (Metraipolis archive dc_69a631973e43, sha256 ff12c6ac294425db6c0dce834d3951150fa80ffb1b25575d85cf920c7fb06485)
BibTeX
@misc{dc69a631973e43,
  title = {Zero-Shot Learning — Wikipedia (de)},
  howpublished = {Wikipedia (de)},
  url = {https://de.wikipedia.org/wiki/Zero-Shot_Learning},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_69a631973e43; sha256 ff12c6ac294425db6c0dce834d3951150fa80ffb1b25575d85cf920c7fb06485},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (de), https://de.wikipedia.org/wiki/Zero-Shot_Learning. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Zero-Shot Learning (englisch, auf Deutsch Nullschusslernen) bezeichnet Verfahren des maschinellen Lernens, bei denen ein Modell Dinge Klassen zuordnen soll, ohne dass es für diese Klassen im Training beschriftete Beispiele (gelabelte Daten) gesehen hat. Damit das trotzdem gelingt, nutzen solche Modelle zusätzliches Wissen über die Klassen, zum Beispiel Attribute oder Textbeschreibungen, die als „Brücke“ zu den (unbekannten) Klassen dienen.

Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «Großes Sprachmodell»).
Fonte: Wikipedia in tedesco, voce «Zero-Shot Learning» — https://de.wikipedia.org/wiki/Zero-Shot_Learning
Wikidata Q96416030: «problem setup in machine learning, where at test time, a learner observes samples from classes that were not observed during training, and needs to predict the class they belong to» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q96416030
Autori: i contributori di Wikipedia (cronologia: https://de.wikipedia.org/wiki/Zero-Shot_Learning?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 267763843, consultata il 2026-10-06T09:48:08.669Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 3cc4df9c93d9df3004d9b0e5d85d66cea5fccd78da4f3f2682af95792f35c04f