.png){kind=icon}
Return
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}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
Continuous time Bayesian networks
Context
Structured conditional intensity matrix
Hierarchical clustering
Trees
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
3.0K
Citations:
5.1K
Organization
Cited Papers
TRIM28 Mediates Primer Binding Site-Targeted Silencing of Murine Leukemia Virus in Embryonic Cells.png)
CellOAAI
CellIF0
OAAIShareSaveShareSaveShareSaveMitochondrial Specific H2Sn Fluorogenic Probe for Live Cell Imaging by Rational Utilization of a Dual-Functional-Photocage GroupACS Sensors
ACS SensorsIF0
PREAI
ShareSave
View more