Graphical Explanation in Belief Networks

By David Madigan, K. Mosurski, R. Almond. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning theory analysis for association rules and sequential event prediction (2013, methodology): “Many authors have emphasized the importance of interpretability and explanation in predictive modeling (see, for example, the work of Madigan et al., 1997).”
Explaining Classifications For Individual Instances (2008, background): “[29] in their belief networks use each (binary or multivalued discrete) attribute as a node in the graph.”
A two-phase method for extracting explanatory arguments from Bayesian networks (2017, background): “[42] construct visual explanations of a Bayesian network based on the graphical structure of the BN and a measure similar to the likelihood ratio but they ignore conditional independence captured by the BN and instead first discard the directions of edges.”
Learning Bayesian networks: approaches and issues (2011, background): “are described by Meek (1995), Verma and Pearl (1992) and Dor and Tarsi (1992).”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, unknown): “Later research focused on explaining Bayesian Belief Networks [102, 126] and Case-Base Reasoning systems [159], following the trends of research interest in these AI paradigms.”
Explaining machine learning models in sales predictions (2017, background): “Madigan et al. (1997) considered the case of belief networks and used each (binary or multi-valued discrete) attribute as a node in the graph.”
Bayesian Artificial Intelligence (2004, methodology): “GRAPHICALBELIEF [178] is an explanatory system that provides a graphical visualization of how evidence propagates through a BN.”