arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1304.3103cs.AI
收藏

学习因果树中的链接概率

Learning Link-Probabilities in Causal Trees

UCLA(加州大学洛杉矶分校)

Igor Roizer, Judea Pearl

摘要:

本文提出了一种学习算法,该算法在给定因果树结构的情况下,仅通过对叶节点的连续测量来估计其连接概率。树的内部节点表示无法观察的概念(隐藏)变量。所描述的方法是增量的,本地的,高效的,并保持强大的测量不精确性。

英文摘要:

A learning algorithm is presented which given the structure of a causal tree, will estimate its link probabilities by sequential measurements on the leaves only. Internal nodes of the tree represent conceptual (hidden) variables inaccessible to observation. The method described is incremental, local, efficient, and remains robust to measurement imprecisions.

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。

↑