.png){kind=icon}
返回
Compact structures for continuous time Bayesian networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.ijar.2019.03.005.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The continuous time Bayesian network (CTBN) is a model capable of describing the probability distribution over a set of variables as it changes in time. The model relies on a directed graph structure to describe direct dependencies between variables, thereby simplifying the underlying parameters that describe the initial distribution and transition behavior. Although this approach can be effective in managing complexity, the size of the model can still be intractable if one variable depends directly on many other variables. To address this issue, we present two methods for imposing additional structure on the model that are capable of capturing regularities in the data that cannot be represented using the CTBN graph structure alone. We demonstrate how these methods can reduce model complexity and compare the representational capabilities of both approaches. (C) 2019 Elsevier Inc. All rights reserved.
Keyword:
Continuous time Bayesian networks
Context
Structured conditional intensity matrix
Hierarchical clustering
Trees
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
3.0K
被引数:
5.1K
机构
引用论文
TRIM28 Mediates Primer Binding Site-Targeted Silencing of Murine Leukemia Virus in Embryonic Cells.png)
CellOAAI
CellIF0
OAAI分享收藏分享收藏Mitochondrial Specific H2Sn Fluorogenic Probe for Live Cell Imaging by Rational Utilization of a Dual-Functional-Photocage GroupACS Sensors
ACS SensorsIF0
PREAI
分享收藏
查看更多内容