PAC学习递归逻辑程序:高效算法
Pac-Learning Recursive Logic Programs: Efficient Algorithms
摘要:
我们提出的算法,学习某些类的无函数递归逻辑程序在多项式时间从等价查询。特别是,我们表明,一个单一的k元递归常数深度确定条款是可学习的。由一个可学习的递归子句和一个常数深度确定的非递归子句组成的两子句程序也是可学习的,如果假设一个额外的“basecase”oracle。这些结果直接暗示了这些类的pac可学习性。虽然这些类的学习递归程序是非常有限的,它是在一个配套文件,他们是最大限度地普遍,在推广任何类以任何自然的方式导致计算困难的学习问题。因此,与它的配套文件,本文建立了一个边界的递归逻辑程序的有效学习。
英文摘要:
We present algorithms that learn certain classes of function-free recursive logic programs in polynomial time from equivalence queries. In particular, we show that a single k-ary recursive constant-depth determinate clause is learnable. Two-clause programs consisting of one learnable recursive clause and one constant-depth determinate non-recursive clause are also learnable, if an additional ``basecase'' oracle is assumed. These results immediately imply the pac-learnability of these classes. Although these classes of learnable recursive programs are very constrained, it is shown in a companion paper that they are maximally general, in that generalizing either class in any natural way leads to a computationally difficult learning problem. Thus, taken together with its companion paper, this paper establishes a boundary of efficient learnability for recursive logic programs.
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。