Title: Darwinian Networks
Authors: Cory J. Butz, Jhonatan de S. Oliveira and André E. dos Santos
Abstract: We suggest Darwinian networks (DNs) as a simplification of reasoning with Bayesian networks (BNs). DNs adapt a handful of well-known concepts in biology into a single framework that is surprisingly simple, yet remarkably robust. With respect to modeling, on one hand, DNs not only represent BNs, but also faithfully represent the testing of independencies in a more straightforward fashion. On the other hand, with respect to two exact inference algorithms in BNs, DNs simplify each of them, while unifying both of them.
In: Proceedings of the Twenty-Eighth Canadian Artificial Intelligence Conference, 16--29
Invited Talk
Title: Introducing Darwinian Networks
Authors: Cory J. Butz
Abstract: Darwinian networks (DNs) are introduced to simplify and clarify working with Bayesian networks (BNs). Rather than modelling the variables in a problem domain, DNs represent the probability tables in the model. The graphical manipulation of the tables then takes on a biological feel. It is shown how DNs can unify modeling and reasoning tasks into a single platform.
In: Proceedings of the Twenty-Eighth International FLAIRS Conference
Title: Determining Good Elimination Orderings with Darwinian Networks
Authors: Cory J. Butz, Jhonatan de S. Oliveira and André E. dos Santos
Abstract: Darwinian networks (DNs) were recently suggested to simplify reasoning with Bayesian networks (BNs). Here we show how DNs can represent four well-known heuristics for determining good elimination orderings in BNs. We propose a new heuristic, called potential energy (PE), based on DNs. Our analysis shows that PE compares favourably with these traditional heuristics.
In: Proceedings of the Twenty-Eighth International FLAIRS Conference, 600--603