首页> 外文会议>Machine learning >Discretizing Continuous Attributes While Learning Bayesian Networks

【24h】

Discretizing Continuous Attributes While Learning Bayesian Networks

机译：学习贝叶斯网络时离散化连续属性

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We introduce a method for learning Bayesian networks that handles the discretization of continuous variables as an integral part of the learning process. The main ingredient in this method is a new metric based on the Minimal Description Length principle for choosing the threshold values for the discretization while learning the Bayesian network structure. This score balances the complexity of the learned discretization and the learned network structure against how well they model the training data. This ensures that the discretization of each variable introduces just enough intervals to capture its interaction with adjacent variables in the network. We formally derive the new metric, study its main properties, and propose an iterative algorithm for learning a discretization policy. Finally, we illustrate its behavior in applications to supervised learning.

机译：我们介绍了一种学习贝叶斯网络的方法，该方法将连续变量的离散化作为学习过程的组成部分进行处理。该方法的主要成分是基于最小描述长度原理的新度量，用于在学习贝叶斯网络结构的同时选择离散化的阈值。该分数将学习的离散化和学习的网络结构的复杂度与他们对训练数据建模的程度进行权衡。这样可以确保每个变量的离散化引入足够的时间间隔以捕获其与网络中相邻变量的交互。我们正式推导了新指标，研究了它的主要特性，并提出了一种学习离散化策略的迭代算法。最后，我们说明了其在监督学习中的行为。

著录项

来源
《Machine learning》|1996年|157-165|共9页
会议地点 Bari(IT);Bari(IT)
作者
Nir Friedman; Moises Goldszmidt;
展开▼
作者单位

Stanford University Dept. of Computer Science Gates Building 1A Stanford, CA 94305-9010;

Rockwell Science Center 444 High St., Suite 400 Palo Alto, CA 94301;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类计算机的应用;
关键词

相似文献

外文文献
中文文献
专利

1. A comparison between discrete and continuous time Bayesian networks in learning from clinical time series data with irregularity [J] . Liu Manxia, Stella Fabio, Hommersom Arjen, Artificial intelligence in medicine . 2019,第APRa期

机译：从不规则的临床时间序列数据中学习离散时间和连续时间贝叶斯网络的比较
2. A comparison between discrete and continuous time Bayesian networks in learning from clinical time series data with irregularity [J] . Liu Manxia, Stella Fabio, Hommersom Arjen, Artificial intelligence in medicine . 2019,第Apra期

机译：不同时间贝叶斯网络学习临床时间序列数据与不规则性的比较
3. Learning Discrete Bayesian Networks from Continuous Data [J] . Yi-Chun Chen, Tim A. Wheeler, Mykel J. Kochenderfer The Journal of Artificial Intelligence Research . 2017,第12期

机译：从连续数据中学习离散贝叶斯网络
4. Bayesian Network Classification with Continuous Attributes: Getting the Best of Both Discretization and Parametric Fitting [C] . Nir Friedman, Moises Goldszmidt, Thomas J. Lee Machine learning . 1998

机译：具有连续属性的贝叶斯网络分类：充分利用离散化和参数拟合
5. Discretizing Continuous Attributes of a Bayesian Network with a Birth and Death Process Based on Minimum Description Length [D] . Woytarowicz, Nicole. 2018

机译：基于最小描述长度与出生和死亡过程的连续属性离散化贝叶斯网络的连续属性
6. CGBayesNets: Conditional Gaussian Bayesian Network Learning and Inference with Mixed Discrete and Continuous Data [O] . Michael J. McGeachie, Hsun-Hsien Chang, Scott T. Weiss 2014

机译：CGBayesNets：带混合离散和连续数据的条件高斯贝叶斯网络学习和推理
7. Learning Discrete Bayesian Networks from Continuous Data [O] . Chen, Yi-Chun, Wheeler, Tim Allan, Kochenderfer, Mykel John 2015

机译：从连续数据中学习离散贝叶斯网络
8. Mix-nets: Factored Mixtures of Gaussians in Bayesian Networks With Mixed Continuous and Discrete Variables [R] . Davies, S. , Moore, A. 2000

机译：混合网：贝叶斯网络中具有混合连续和离散变量的高斯分解因子

Discretizing Continuous Attributes While Learning Bayesian Networks

摘要

著录项

相似文献

相关主题

期刊订阅