Metraipolis › archive › dc_8ca5fdea4d5e
Probably approximately correct learning — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Probably_approximately_correct_learning
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-05T23:52:18.628Z
- SHA-256 of the archived text
bd75e72a984d50d927da9a28e7684556eeb435991da1aeedc3701a6e1f4e94e0- Stable URL of this page
https://metraipolis.com/documento/dc_8ca5fdea4d5e
How to cite
Probably approximately correct learning — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Probably_approximately_correct_learning (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_8ca5fdea4d5e (Metraipolis archive dc_8ca5fdea4d5e, sha256 bd75e72a984d50d927da9a28e7684556eeb435991da1aeedc3701a6e1f4e94e0)
BibTeX
@misc{dc8ca5fdea4d5e,
title = {Probably approximately correct learning — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Probably_approximately_correct_learning},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_8ca5fdea4d5e; sha256 bd75e72a984d50d927da9a28e7684556eeb435991da1aeedc3701a6e1f4e94e0},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Probably_approximately_correct_learning. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In computational learning theory, probably approximately correct (PAC) learning is a framework for mathematical analysis of machine learning. It was proposed in 1984 by Leslie Valiant. In this framework, the learner receives samples and must select a generalization function (called the hypothesis) from a certain class of possible functions. The goal is that, with high probability (the "probably" part), the selected function will have low generalization error (the "approximately correct" part). The learner must be able to learn the concept given any arbitrary approximation ratio, probability of success, or distribution of the samples. The model was later extended to treat noise (misclassified samples). An important innovation of the PAC framework is the introduction of computational complexity theory concepts to machine learning. In particular, the learner is expected to find efficient functions (time and space requirements bounded to a polynomial of the example size), and the learner itself must implement an efficient procedure (requiring an example count bounded to a polynomial of the concept size, modified by the approximation and likelihood bounds). Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «reinforcement learning»). Fonte: Wikipedia in inglese, voce «Probably approximately correct learning» — https://en.wikipedia.org/wiki/Probably_approximately_correct_learning Wikidata Q458526 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q458526 Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Probably_approximately_correct_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 1369851981, consultata il 2026-10-05T23:21:46.348Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 821d74d8d86c8f86630f173e3f377629b83098ba59fee0b610ae770731c8dfa2