arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1711.04438cs.AI
收藏

部分可观察性下的学习溯因

Learning Abduction under Partial Observability

Washington University in St. Louis(圣路易斯华盛顿大学)

Brendan Juba, Zongyi Li, Evan Miller

摘要:

Juba最近提出了一个从例子中学习溯因推理的公式,其中各种解释的相对可解释性以及哪些解释是有效的,都是直接从数据中学习的。这种任务表述的主要缺点是它假设可以获得全部信息(即,完全指定的)示例;相对地,它没有为陈述性背景知识提供作用,因为这种知识在完全信息的溯因任务中是多余的。在这项工作中,我们扩展了配方,利用这些部分指定的例子,以及声明性的背景知识的缺失数据。我们表明,它是可能的,使用内隐学习的规则与明确给出的陈述性知识,以支持假设的过程中的溯因推理。我们观察到,当一个小的解释存在,它是可能的,以获得一个大大改善的保证在具有挑战性的异常容忍设置。这种小的,人类可以理解的解释是特别感兴趣的潜在应用的任务。

英文摘要:

Juba recently proposed a formulation of learning abductive reasoning from examples, in which both the relative plausibility of various explanations, as well as which explanations are valid, are learned directly from data. The main shortcoming of this formulation of the task is that it assumes access to full-information (i.e., fully specified) examples; relatedly, it offers no role for declarative background knowledge, as such knowledge is rendered redundant in the abduction task by complete information. In this work, we extend the formulation to utilize such partially specified examples, along with declarative background knowledge about the missing data. We show that it is possible to use implicitly learned rules together with the explicitly given declarative knowledge to support hypotheses in the course of abduction. We observe that when a small explanation exists, it is possible to obtain a much-improved guarantee in the challenging exception-tolerant setting. Such small, human-understandable explanations are of particular interest for potential applications of the task.

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。

↑