通过随机化和最大似然法快速估计关系模式覆盖Fast Estimation of Relational Pattern Coverage through Randomization and Maximum Likelihood |
|
课程网址: | http://videolectures.net/icml08_kuzelka_fer/ |
主讲教师: | Ondřej Kuželka |
开课单位: | 布拉格捷克技术大学 |
开课时间: | 2008-07-28 |
课程语种: | 英语 |
中文简介: | 在归纳逻辑编程中,theta包含是一种广泛使用的覆盖测试。不幸的是,测试theta包含是NP完成的,这代表了许多关系学习者的关键效率瓶颈。在本文中,我们提出了基于随机重启搜索策略的子句覆盖的概率估计。在分布假设下,我们的算法可以估计子句覆盖,而无需为所有示例确定包含。我们在程序ReCovEr中实现了这个算法。在生成的图形数据和现实世界数据集上,我们表明ReCovEr提供了相当准确的估计,同时与最先进的算法相比实现了显着的运行时间改进 |
课程简介: | In inductive logic programming, theta-subsumption is a widely used coverage test. Unfortunately, testing theta-subsumption is NP-complete, which represents a crucial efficiency bottleneck for many relational learners. In this paper, we present a probabilistic estimator of clause coverage, based on a randomized restarted search strategy. Under a distribution assumption, our algorithm can estimate clause coverage without having to decide subsumption for all examples. We implement this algorithm in program ReCovEr. On generated graph data and real-world datasets, we show that ReCovEr provides reasonably accurate estimates while achieving dramatic runtimes improvements compared to a state-of-the-art algorithm |
关 键 词: | 归纳逻辑编程; 覆盖测试; 概率估计 |
课程来源: | 视频讲座网 |
最后编审: | 2019-04-19:lxf |
阅读次数: | 6 |