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 1304.2377cs.AI
收藏

多连通信度网络中的更新概率

Updating Probabilities in Multiply-Connected Belief Networks

Stanford University(斯坦福大学)

Jaap Suermondt, Gregory F. Cooper

摘要:

本文主要研究多连通信度网络中的概率更新问题。Pearl设计了调节的方法,这使我们能够通过为网络选择一个环割集并实例化这些环割集节点,将他在单连接网络中的信念更新算法应用于多连接信念网络。我们讨论所选节点需要满足的条件。我们提出了一个启发式算法找到一个循环割集,满足这些条件。

英文摘要:

This paper focuses on probability updates in multiply-connected belief networks. Pearl has designed the method of conditioning, which enables us to apply his algorithm for belief updates in singly-connected networks to multiply-connected belief networks by selecting a loop-cutset for the network and instantiating these loop-cutset nodes. We discuss conditions that need to be satisfied by the selected nodes. We present a heuristic algorithm for finding a loop-cutset that satisfies these conditions.

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。

↑