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
- triangular truncation
- triangulated
- triangulated category
- triangulated equivalence
- triangulated functor
- triangulated irregular network data model
- triangulated manifold
- triangulated pair
- triangulated space
- triangulated subcategory
- triangulated surface
- triangulateration
- triangulateration network
- triangulating
- triangulation
- triangulation algorithm
- triangulation based measurement
- triangulation chain
- triangulation grid
- triangulation invariant
- triangulation measuring distance
- triangulation network
- Triangulation of implicit surfaces
- triangulation point
- triangulation problem