学习小度结构上的一阶可定义概念
Learning first-order definable concepts over structures of small degree
摘要:
我们考虑一个声明性的框架机器学习的概念和假设定义的逻辑公式在一些背景结构。我们表明,在这个框架内,一阶公式定义的概念,在最多的polylogarithmic度的背景结构可以学习在polylogarithmic时间在“可能近似正确”的学习意义。
英文摘要:
We consider a declarative framework for machine learning where concepts and hypotheses are defined by formulas of a logic over some background structure. We show that within this framework, concepts defined by first-order formulas over a background structure of at most polylogarithmic degree can be learned in polylogarithmic time in the "probably approximately correct" learning sense.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。