arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1406.1111math.LOcs.LGcs.LO
收藏

PAC学习、VC维度和算术层次

PAC Learning, VC Dimension, and the Arithmetic Hierarchy

Southern Illinois University, Carbondale(南伊利诺伊大学卡本代尔分校)

Wesley Calvert

摘要:

我们计算出PAC可学习的概念类的索引集是$m$ -完备的$Σ^0_3$,在所有合理形式的概念类的索引集内。考虑的所有概念类都是可计算$Π^0_1$类的可计算枚举,在某种意义上在这里是精确的。这个概念类族足以覆盖所有标准示例,并且还具有PAC可学习性等价于有限VC维的性质。

英文摘要:

We compute that the index set of PAC-learnable concept classes is $m$-complete $Σ^0_3$ within the set of indices for all concept classes of a reasonable form. All concept classes considered are computable enumerations of computable $Π^0_1$ classes, in a sense made precise here. This family of concept classes is sufficient to cover all standard examples, and also has the property that PAC learnability is equivalent to finite VC dimension.

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。

↑