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
- anti scorching agent
- anti-scorching agent
- antisecant
- Anti-Secession Law of the People's Republic of China
- anti-seepage for groundwater pollution
- anti-seismic ability of nuclear power plant
- anti seismic structural measures
- antiselena
- anti-self-adjoint operator
- anti self dual connection
- anti-self-dual connection
- anti-selfdual connection
- anti-selfdual form
- anti-selfdual metric
- anti-semi-invariant
- antisense gene
- anti sense imaging
- anti-sense imaging
- antisense imaging
- antisense nuclear acid imaging agent
- antisense oligodeoxynucleotide，AS-ODN
- antisense RNA
- antisense strand
- antisensitization
- antisepsis