arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08183cs.CVstat.APstat.ML
收藏

基于阴影映射的无监督神经元因果发现

Shadow-Mapping for Unsupervised Neural Causal Discovery

University of Surrey(萨里大学)

Matthew J. Vowels, Necati Cihan Camgoz, Richard Bowden

摘要:

大多数科学领域的一个重要目标是发现一组观察结果的因果结构。遗憾的是,基于相关性或互信息的因果发现方法常常不能识别呈现动态关系的系统中的因果链接。这种动态系统(包括著名的耦合逻辑斯蒂映射)表现出“海市蜃楼”的相关性,其出现和消失取决于观察窗口。这不仅意味着相关性不是因果关系,而且可能与直觉相反,因果关系可能在没有相关性的情况下发生。在本文中,我们描述了神经阴影映射,一个基于神经网络的方法,将高维视频数据嵌入到一个低维的阴影表示,随后的因果关系的估计。我们展示了它的性能在发现因果关系的动态系统的视频表示。

英文摘要:

An important goal across most scientific fields is the discovery of causal structures underling a set of observations. Unfortunately, causal discovery methods which are based on correlation or mutual information can often fail to identify causal links in systems which exhibit dynamic relationships. Such dynamic systems (including the famous coupled logistic map) exhibit `mirage' correlations which appear and disappear depending on the observation window. This means not only that correlation is not causation but, perhaps counter-intuitively, that causation may occur without correlation. In this paper we describe Neural Shadow-Mapping, a neural network based method which embeds high-dimensional video data into a low-dimensional shadow representation, for subsequent estimation of causal links. We demonstrate its performance at discovering causal links from video-representations of dynamic systems.

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。

↑