Temporal Abstraction in Bayesian Networks

Abstract

A current popular approach to representing time in Bayesian belief networks is through Dynamic Bayesian Networks (DBNs) (Dean & Kanazawa, 1989). DBNs connect sequences of entire Bayes networks, each representing a situation at a snapshot in time. The authors present an alternative method for incorporating time into Bayesian belief networks that utilizes abstractions of temporal representations. This method maintains the principled Bayesian approach to reasoning under uncertainty, providing explicit representation of sequence and potentially complex temporal relationships, while also decreasing overall network complexity compared to DBNs.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2003
Accession Number
ADA459894

Entities

People

  • Brendan Burns
  • Clayton T. Morrison

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Autonomous Agents
  • Bayesian Networks
  • Collision Avoidance
  • Collisions
  • Construction
  • Detectors
  • Engineering
  • Expert Systems
  • Intervals
  • Machine Learning
  • Models
  • Probabilistic Models
  • Probability
  • Time Intervals

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computer Networking

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference