Learning the Structure of Dynamic Probabilistic Networks

Abstract

Dynamic probabilistic networks are a compact representation of complex stochastic processes. In this paper we examine how to learn the structure of a DPN from data. We extend structure scoring rules for standard probabilistic networks to the dynamic case, and show how to search for structure when some of the variables are hidden. Finally, we examine two applications where such a technology might be useful: predicting and classifying dynamic behaviors, and learning causal orderings in biological processes. We provide empirical results that demonstrate the applicability of our methods in both domains.

Appears in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998)

References in corpus (2)

• The Bayesian Structural EM Algorithm
• Tractable Inference for Complex Stochastic Processes

Cited by in corpus (12)

• Dynamic Bayesian Multinets
• Bayesian structure learning using dynamic programming and MCMC
• Regret-based Reward Elicitation for Markov Decision Processes
• The Temporal Logic of Causal Structures
• Learning Why Things Change: The Difference-Based Causality Learner
• Discovering the Hidden Structure of Complex Dynamic Systems
• The Infinite Latent Events Model
• Inferring Dynamic Bayesian Networks using Frequent Episode Mining
• Learning Selectively Conditioned Forest Structures with Applications to DBNs and Classification
• Intuitive visualization of the intelligence for the run-down of terrorist wire-pullers
• Reading Dependencies from Polytree-Like Bayesian Networks
• Positive factor networks: A graphical framework for modeling non-negative sequential data