arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.03744cs.AI
收藏

P-Tree编程

P-Tree Programming

University of Basel(巴塞尔大学)

Christian Oesch

摘要:

提出了一种新的程序合成方法。P-树编程通过一棵概率原型树来表示程序的搜索空间。从这个原型树,我们形成程序实例,我们评估一个给定的问题。来自评估的错误值通过原型树传播。我们使用它们来更新概率分布,以确定进一步实例的符号选择。迭代法适用于几个符号回归基准从文献。它在很大程度上优于标准的遗传编程。此外,它依赖于一组简洁的参数,这些参数对所有问题都保持不变。该算法可用于大多数典型的计算智能任务,如分类,自动程序归纳,符号回归。

英文摘要:

We propose a novel method for automatic program synthesis. P-Tree Programming represents the program search space through a single probabilistic prototype tree. From this prototype tree we form program instances which we evaluate on a given problem. The error values from the evaluations are propagated through the prototype tree. We use them to update the probability distributions that determine the symbol choices of further instances. The iterative method is applied to several symbolic regression benchmarks from the literature. It outperforms standard Genetic Programming to a large extend. Furthermore, it relies on a concise set of parameters which are held constant for all problems. The algorithm can be employed for most of the typical computational intelligence tasks such as classification, automatic program induction, and symbolic regression.

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。

↑