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
- United Nations International Law Commission
- United Nations Interregional Crime and Justice Research Institute
- United Nations Model Double Taxation Convention between Developed and Developing Countries
- United Nations Office for Outer Space Affairs
- United Nations Office for Outer Space Affairs（UNOOSA）
- United Nations Office on Drug and Crime
- United Nations operation in Somalia
- United Nations Peace-keeping Forces
- United Nations Population and Development Commission
- United Nations Population Division
- United Nations publications
- United Nations Radio
- United Nations Relief and Rehabilitation Administration
- United Nations Road Safety Collaboration, UNRSC
- United Nations rule of law
- United Nations Scientific Committee on the Effects of Atomic Radiation
- united nations scientific committee on the effects of atomic radiation
- United Nations soil management
- United Nations Special Committee Decolonization
- United Nations standards in criminal justice
- United Nations Statistics Division
- United Nations Summit on Sustainable Development 2015
- United Nations Trusteeship Council
- United Nations University
- United Nations World Assembly on Ageing