基于概念学习的归纳程序综合

Inductive Program Synthesis by Concept Learning

本文介绍一种基于概念学习的归纳程序综合方法.假设的形成和证实是归纳过程的两个主要步骤.本文所介绍的方法是利用问题的背景知识、通过推广形成假设,并采用自动构作临界实例技术加以证实.

A method of inductive program synthesis by concept learning is presented in this paper. Hypothesis formation and validation are the two main processes of induction. In our method, hypotheses are formed and generalized according to the background knowledge. The technique of automatic construction of critical examples is adopted to validate the formed hypotheses.