理学 学习理论 释 PAC learning PAC学习 PAC (Probably Approximately Correct)学习，中文翻译为概率近似正确学习，是计算学习理论中最重要的研究内容之一，由图灵奖得主Valiant [1]于1984年首先提出的学习框架。PAC学习给出了一种数学形式化刻画机器学习的框架，基于此框架，很多学习问题得以从理论上进一步探讨，如什么样的学习任务是可以学习的。
人工智能 机器学习 释文 probably approximately correct learning 概率近似正确学习
- nonparametric regression
- nonparametric regression model
- nonparametric representation
- non-parametric statistics
- nonparametric statistics
- Non-parametric Test
- nonparametric test
- nonparametric theory
- nonparametric tolerance limit
- non-paroxysmal atrioventricular junctional tachycardia
- non-participational observation method
- nonparticipation observation
- Non-Party-Polity
- non-Pascalian geometry
- non-Pascal probability logic
- non-perfect information
- non-perfect set
- non-perfect space
- non-performance of obligation
- non-performing asset ratio
- nonperiodic
- non-periodic comet
- nonperiodic decimal
- nonperiodic function
- non-periodic motion