Improved Sampling for Diagnostic Reasoning in Bayesian Networks
نویسنده
چکیده
Bayesian networks offer great potential for use in automating large scale diagnostic rea soning tasks. Gibbs sampling is the main technique used to perform diagnostic reason ing in large richly interconnected Bayesian networks. Unfortunately Gibbs sampling can take an excessive time to generate a represen tative sample. In this paper we describe and test a number of heuristic strategies for im proving sampling in noisy-or Bayesian net works. The strategies include Monte Carlo Markov chain sampling techniques other than Gibbs sampling. Emphasis is put on strate gies that can be implemented in distributed systems.
منابع مشابه
Load-Frequency Control: a GA based Bayesian Networks Multi-agent System
Bayesian Networks (BN) provides a robust probabilistic method of reasoning under uncertainty. They have been successfully applied in a variety of real-world tasks but they have received little attention in the area of load-frequency control (LFC). In practice, LFC systems use proportional-integral controllers. However since these controllers are designed using a linear model, the nonlinearities...
متن کاملImportance Sampling for Bayesian
Bayesian networks (BNs) offer a compact, intuitive, and efficient graphical representation of uncertain relationships among the variables in a domain and have proven their value in many disciplines over the last two decades. However, two challenges become increasingly critical in practical applications of Bayesian networks. First, real models are reaching the size of hundreds or even thousands ...
متن کاملThe Effect of Bayesian Reasoning Training on the Results of Clinical Reasoning Tests of Interns
Introduction: Clinical reasoning includes a range of thinking about clinical medicine at all stages of patient evaluation. Bayesian theory can be used to refute or confirm differential diagnoses in the clinical reasoning process. In this way, by learning the basic mathematical language of probability in medicine, we can change our beliefs according to new evidence. The aim of this study is to i...
متن کاملImportance sampling algorithms for Bayesian networks: Principles and performance
Precision achieved by stochastic sampling algorithms for Bayesian networks typically deteriorates in the face of extremely unlikely evidence. In addressing this problem, importance sampling algorithms seem to be most successful. We discuss the principles underlying the importance sampling algorithms in Bayesian networks. After that, we describe Evidence Pre-propagation Importance Sampling (EPIS...
متن کاملLocal Importance Sampling in Multiply Sectioned Bayesian Networks
The multiply sectioned Bayesian network (MSBN) is a well-studied model for probability reasoning in a multiagent setting. Exact inference, however, becomes difficult as the problem domain grows larger and more complex. We address this issue by integrating approximation techniques with the MSBN Linked Junction Tree Forest (LJF) framework. In particular, we investigate the application of importan...
متن کامل