Discriminative learning of Bayesian networks for data mining applications

用于数据挖掘应用的贝叶斯网络的判别学习

• 批准号: 261282-2007
• 负责人: Zhang, Huajie
• 金额: $ 1.6万
• 依托单位: University of New Brunswick
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2009
• 资助国家: 加拿大
• 起止时间: 2009-01-01 至 2010-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=426527
• 关键词: Discriminative; learning; Bayesian; networks; data

Bayesian networks (BNs) have been widely used in data mining applications, in which learning a BN from data is crucial. Most BN learning algorithms learn a joint distribution over all the variables to best fit the training data, i.e. generative learning. Discriminative learning directly targets a task-specific model, instead of a generative model, and demonstrates superior performance. Discriminatively learning a BN includes two steps: structure learning and parameter learning. Structure learning determines the structure of a BN, and parameter learning sets the local distribution for each variable.

贝叶斯网络在数据挖掘中得到了广泛的应用，其中从数据中学习贝叶斯网络至关重要。大多数BN学习算法学习所有变量上的联合分布以最好地匹配训练数据，即生成性学习。鉴别性学习直接针对特定于任务的模式，而不是生成性模式，表现出优异的表现。判别学习包括两个步骤：结构学习和参数学习。结构学习确定BN的结构，参数学习设置每个变量的局部分布。