In Maximum Entropy and Bayesian Methods, W. von der Linden, et al., eds., pp. 309-318 (Kluwer Academic, Dordrecht, 1999)

Operation of the Bayes Inference Engine

Kenneth M. Hanson and Gregory S. Cunningham
Los Alamos National Laboratory

Abstract

We have developed a computer application, called the Bayes Inference Engine, to enable us to make inferences about models of a physical object from radiographs taken of it. In the BIE calculational models are represented by a data-flow diagram that can be manipulated by the analyst in a graphical-programming environment. We demonstrate the operation of the BIE in terms of examples of two-dimensional tomographic reconstruction including uncertainty estimation.

Keywords: Bayesian analysis, MAP estimator, uncertainty estimation, radiographic modeling, Markov chain Monte Carlo, adjoint differentiation, object oriented design

Get full paper (pdf, 506 KB)
Return to publication list
Send e-mail to author at kmh@hansonhub.com