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
- algebraic symbol
- algebraic system
- algebraic tangle
- algebraic tensor product
- algebraic theorem
- algebraic theory
- algebraic theory of linear systems
- algebraic theory of numbers
- algebraic topology
- algebraic torus
- algebraic transformation
- algebraic transformation group
- algebraic transformation space
- algebraic unit
- algebraic unknotting number
- algebraic value
- algebraic variety
- algebraic variety of general type
- algebraic vector bundle
- algebraic version of the Gauss Manin connection
- algebraic version of the Gauss-Manin connection
- algebra isomorphism
- algebraist
- algebraizable
- algebraizable sheaf