Matches in DBpedia 2016-04 for { <http://wikidata.dbpedia.org/resource/Q458526> ?p ?o }
Showing triples 1 to 20 of
20
with 100 triples per page.
- Q458526 subject Q11275242.
- Q458526 abstract "In computational learning theory, probably approximately correct learning (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).".
- Q458526 wikiPageExternalLink pac.pdf.
- Q458526 wikiPageExternalLink www.probablyapproximatelycorrect.com.
- Q458526 wikiPageWikiLink Q11275242.
- Q458526 wikiPageWikiLink Q1339385.
- Q458526 wikiPageWikiLink Q167555.
- Q458526 wikiPageWikiLink Q172491.
- Q458526 wikiPageWikiLink Q205084.
- Q458526 wikiPageWikiLink Q2462783.
- Q458526 wikiPageWikiLink Q2539.
- Q458526 wikiPageWikiLink Q2662236.
- Q458526 wikiPageWikiLink Q43260.
- Q458526 wikiPageWikiLink Q45284.
- Q458526 wikiPageWikiLink Q5158394.
- Q458526 wikiPageWikiLink Q5362437.
- Q458526 wikiPageWikiLink Q544369.
- Q458526 wikiPageWikiLink Q93154.
- Q458526 comment "In computational learning theory, probably approximately correct learning (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.".
- Q458526 label "Probably approximately correct learning".