An Algorithm of Bayesian Networks Parameters Learning Based on Confidence Interval

摘要：

This paper focuses on an interval parameter estimation of Bayesian Networks (BNs). Contrast to the point estimation used in most parameter learning algorithms, interval estimation algorithm (IEA) estimates the output nodes parameter of BNs with an interval estimation based on confidence level, it can raise BNs inference accuracy slightly as the prior knowledge is absence.

关键词： Bayesian networks parameter learning confidence interval estimation

作者: Tilong Wang Lihong Guo Yan Li

作者单位: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences Changchun, Ch Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences Changchun, Ch

会议类型: 国际会议

会议名称: 2010 International Conference on Computer,Mechatronics,Control and Electronic Engineering(2010计算机、机电、控制与电子工程国际会议 CMCE 2010)

会议地点: 长春

会议语种:英文

页码: 233-235

在线出版日期: 2010-08-24（万方平台首次上网日期，不代表论文的发表时间）