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 1301.0590cs.AI
收藏

用于可扩展监测的因子粒子

Factored Particles for Scalable Monitoring

Harvard University(哈佛大学)

Brenda Ng, Leonid Peshkin, Avi Pfeffer

摘要:

动态贝叶斯网络的精确监测是一个棘手的问题,因此近似算法是必要的。本文提出了一种新的家庭的近似监测算法,结合粒子滤波和Boyen-Koller方法的最佳品质。我们的算法保持一个近似表示的信念状态的形式组的因子化粒子,对应于状态变量的集群的样本。实验结果表明,我们的算法优于普通粒子滤波和Boyen-Koller算法在大型系统。

英文摘要:

Exact monitoring in dynamic Bayesian networks is intractable, so approximate algorithms are necessary. This paper presents a new family of approximate monitoring algorithms that combine the best qualities of the particle filtering and Boyen-Koller methods. Our algorithms maintain an approximate representation the belief state in the form of sets of factored particles, that correspond to samples of clusters of state variables. Empirical results show that our algorithms outperform both ordinary particle filtering and the Boyen-Koller algorithm on large 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。

↑