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
- land type
- land type map
- land unit
- landup performance of carrier-based aircraft
- land usage permit system
- land use
- land use and cover change
- Land Use and Land Cover Change Project
- land use arrangement planning of central city area
- land use classification
- land use control
- land use control system
- land use conveyance
- land use degree
- land-use density
- land used for industry and mining storage purposes
- land used for public manegement and service
- land used for special purposes
- land-use division
- land use engineering
- land use information
- land use intensity
- land use management
- land use map
- land-use model