D
David Poole
Researcher at University of British Columbia
Publications - 229
Citations - 12337
David Poole is an academic researcher from University of British Columbia. The author has contributed to research in topics: Probabilistic logic & Bayesian network. The author has an hindex of 45, co-authored 228 publications receiving 11736 citations. Previous affiliations of David Poole include Canadian Institute for Advanced Research & University of Waterloo.
Papers
More filters
Proceedings ArticleDOI
Predicting Landslides Using Locally Aligned Convolutional Neural Networks
TL;DR: Locally aligned convolutional neural network (LACNN) as discussed by the authors was proposed to follow the ground surface at multiple scales to predict possible landslide occurrence for a single point, and compared with several baselines, including linear regression, a neural network, and a CNN, using log-likelihood error and Receiver Operating Characteristic curves on the test set.
Who chooses the assumptions
TL;DR: This paper shows how a number of nonmonotonic reasoning probabilistic reasoning and design can be combined into a coherent logic based abductive framework based on allowing consistent assumptions to be used to prove a goal.
Book ChapterDOI
Adding Local Constraints to Bayesian Networks
TL;DR: shielded Bayesian networks provide a novel method for implementing chain graphs with existing Bayesian network tools and are compared to chain graphs which allow undirected and directed edges and which model equivalent distributions.
Sequential updating conditional probability in Bayesian networks by posterior probability
TL;DR: A new algorithm (ALPP) is presented that allows refinement of FCPs based on expert estimates of posterior probability and applies to any DAG of diameter 1.
Journal ArticleDOI
Combining logic and probability
Eric Neufeld,David Poole +1 more
TL;DR: It is argued that the appropriate way to use logic is in the form of theory formation, and the appropriate role of probability is as a theory comparator in the same framework as logical and probabilistic reasoning.